Analytics Septemberoctober 2014
Content
H T T P : / / WWW. A N A L Y T I C S - MAGA Z I N E . O R G
SEPTEMBER/ OCTOBER 2014 DRIVING BETTER BUSINESS DECISIONS
BROUGHT TO YOU BY:
MEASURING SOCIAL
MEDIA KARMA
Five easy-to-extract
metrics of posts,
tweets, blogs, pings and
uploads from a vast,
unstructured world
ALSO INSIDE:
• 10 myths of analytics and insights
• High-performance analytics companies
• Can technology transform government?
• The value of ‘wrangling data’ skills
Executive Edge
Verisk Analytics CEO
Scott Stephenson on
innovation redefined:
beyond investing
in technology
WWW. I NF OR MS . OR G 2 | A NA LY T I CS - MAGA Z I NE . OR G
Slaying sacred cows
I NSI DE STORY
Slaying metaphorical sacred cows is
hard work, but that’s exactly what Will
Towler does in this month’s lead fea-
ture article (“10 myths of analytics and
insights”). Among the myths Towler de-
bunks: “Knowledge is power,” “People
are rational,” “You can’t manage what you
can’t measure,” “Sound analytics drive
sound decision-making” and my personal
favorite, “Great insights sell themselves.”
Any analytics professional who has
ever bumped up against corporate deci-
sion-makers has been there, done that,
been dismissed, picked up the pieces
and analyzed what went wrong.
By defnition, metaphorical sacred
cows are “considered to be exempt from
criticism or questioning,” so they must be
approached with caution. Yet Towler not
only takes them on, he offers some valu-
able takeaways. For more click here.
Speaking of measuring, Mu Sigma
manager Kshira Saagar provides fve
fundamental measures that can serve as
quick-wins to analyze your social media
karma. Saagar notes that while almost
every organization spends lots of fnan-
cial and human resources trying to make
sense of their social media actions (post,
tweet, blog, ping, upload, etc.) and reac-
tions (like, share, re-tweet, favorite, re-
blog and download), about half of chief
marketing offcers are unable to quantify
social media impact on their companies.
Warns Saagar: “In this interconnected
world, a small social media ripple can
have the impact of a tsunami on the even-
tual sales bottom line.”
Harrison Schramm, CAP, author of
“The Five-Minute Analyst” column, turned
his textual data tools loose on an unusual
target this issue: presidents’ State of the
Union addresses over the years. Sch-
ramm used a method call the “Flesch-
Kincaid Grade Level” to calculate the
readability and complexity of frst-term
State of the Union addresses by Presi-
dents Madison, Lincoln, Clinton, Bush
(George W.) and Obama. To see how
they graded out, click here.
In case you were wondering, the “CAP”
after Schramm’s name indicates he’s a
Certifed Analytics Professional (CAP
®
).
Developed by INFORMS, the CAP pro-
gram includes an exam that is adminis-
tered at more than 700 testing locations
around the world. The CAP program was
recently listed No. 1 by CIO magazine in
an article titled, “11 Big Data Certifcations
That Will Pay Off.” For more on the CAP
story, click here.
– PETER HORNER, EDITOR
peter.horner
@
mail.informs.org
OPTIMIZE
YOUR BUSINESS
WITH UNPRECEDENTED
SPEED
[email protected] | +1 425 458 4024
To learn more about AIMMS Optimization Apps, visit aimms.com.
TO YOUR ENTERPRISE
OPTIMIZATION
APP STORE
PUBLISHED
INSTANTLY
IN A FEW
DAYS
PROOF OF
CONCEPT
IN A FEW
WEEKS
OPTIMIZATION APP
IN A FEW
MONTHS
MISSION CRITICAL
ENTERPRISE APP
IN A FEW
HOURS
IDEA
WWW. I NF OR MS . OR G 4 | A NA LY T I CS - MAGA Z I NE . OR G
DRIVING BETTER BUSINESS DECISIONS
C O N T E N T S
FEATURES
10 MYTHS OF ANALYTICS AND INSIGHTS
From traditional consumer research to emerging business
intelligence, 10 fallacies to keep in mind to make the most
of your analytical efforts.
By Will Towler
HIGH-PERFORMANCE ANALYTICS ORGANIZATIONS
To realize value from big data analytics, organizations need to
integrate technology, tools and practices with existing analytics
ecosystems.
By Pramod Singh, Ritin Mathur and Srujana H.M.
FIVE MEASURES OF SOCIAL MEDIA KARMA
Return on investment: Quick-fix analyses and easy-to-extract
metrics of posts, tweets, blogs, pings and uploads from vast,
unstructured world.
By Kshira Saagar
CAN GOVERNMENT LEAD INNOVATION?
The first U. S. chief technology officer claims great promise for
public-private information technology partnerships.
By Doug Samuelson
30
38
46
54
46
SEPTEMBER/ OCTOBER 2014
Brought to you by
30
54
38
Tel 775 831 0300 • Fax 775 831 0314 • [email protected]
ANALYTIC SOLVER PLATFORM
Visualize, Analyze, Decide with Power BI + Premium Solver
Before your company spends a year and a small fortune
on “advanced analytcs”, shouldn’t you fnd out what
your people can do with the latest enhancements to
the tool they already know – Microsof Excel – in
business intelligence and advanced analytcs today?
Did you know that with Power Pivot in Excel 2013 and
2010, your Excel desktop can easily analyze 100 million
row datasets, with the power of Microsof’s SQL Server
Analysis Services xVelocity engine inside Excel?
Did you know that with Power Query in Excel, you can
extract, transform and load (ETL) data from virtually any
enterprise or cloud database with point-and-click ease?
Did you know that with Analytc Solver Platorm in
Excel, you can create powerful data mining, forecastng
and predictve analytcs models, rivaling the best-known
statstcal packages, again with point-and-click ease?
Did you know that with Analytc Solver Platorm, you can
build sophistcated Monte Carlo simulaton, risk analysis,
conventonal and stochastc optmizaton models, using
the world’s best solvers, and modeling tools proven in
use by over 7,000 companies?
Did you know that with Power View and Frontline’s
XLMiner Data Visualizaton, you can visualize not only
your data, but the results of your analytc models?
Now you know that with Microsof’s Power BI and
Frontline’s Premium Solver App, you can publish your
Excel workbook to Ofce 365 in the cloud, share your
visualizatons, refresh from on-premise databases, and
re-optmize your model for new decisions immediately.
Find Out More, Download Your Free Trial Now
Visit www.solver.com/powerbi to learn more, register
and download a free trial – or email or call us today.
6 |
DRIVING BETTER BUSINESS DECISIONS
REGISTER FOR A FREE SUBSCRIPTION:
http://analytics.informs.org
INFORMS BOARD OF DIRECTORS
President Stephen M. Robinson, University of
Wisconsin-Madison
President-Elect L. Robin Keller, University of
California, Irvine
Past President Anne G. Robinson, Verizon Wireless
Secretary Brian Denton,
University of Michigan
Treasurer Nicholas G. Hall, Ohio State University
Vice President-Meetings William “Bill” Klimack, Chevron
Vice President-Publications Eric Johnson, Dartmouth College
Vice President-
Sections and Societies Paul Messinger, CAP, University of Alberta
Vice President-
Information Technology Bjarni Kristjansson, Maximal Software
Vice President-Practice Activities Jonathan Owen, CAP, General Motors
Vice President-International Activities Grace Lin, Institute for Information Industry
Vice President-Membership
and Professional Recognition Ozlem Ergun, Georgia Tech
Vice President-Education Joel Sokol, Georgia Tech
Vice President-Marketing,
Communications and Outreach E. Andrew “Andy” Boyd,
University of Houston
Vice President-Chapters/Fora David Hunt, Oliver Wyman
INFORMS OFFICES
www.informs.org • Tel: 1-800-4INFORMS
Executive Director Melissa Moore
Meetings Director Laura Payne
Marketing Director Gary Bennett
Communications Director Barry List
Headquarters INFORMS (Maryland)
5521 Research Park Drive, Suite 200
Catonsville, MD 21228
Tel.: 443.757.3500
E-mail: [email protected]
ANALYTICS EDITORIAL AND ADVERTISING
Lionheart Publishing Inc., 506 Roswell Street, Suite 220, Marietta, GA 30060 USA
Tel.: 770.431.0867 • Fax: 770.432.6969
President & Advertising Sales John Llewellyn
[email protected]
Tel.: 770.431.0867, ext. 209
Editor Peter R. Horner
[email protected]
Tel.: 770.587.3172
Assistant Editor Donna Brooks
[email protected]
Art Director Jim McDonald
[email protected]
Tel.: 770.431.0867, ext. 223
Advertising Sales Sharon Baker
[email protected]
Tel.: 813.852.9942
Analytics (ISSN 1938-1697) is published six times a year by the
Institute for Operations Research and the Management Sciences
(INFORMS), the largest membership society in the world dedicated
to the analytics profession. For a free subscription, register at
http://analytics.informs.org. Address other correspondence to
the editor, Peter Horner, [email protected]. The
opinions expressed in Analytics are those of the authors, and
do not necessarily refect the opinions of INFORMS, its offcers,
Lionheart Publishing Inc. or the editorial staff of Analytics.
Analytics copyright ©2014 by the Institute for Operations
Research and the Management Sciences. All rights reserved.
The PuzzlOR & Thinking Analytically
B Y J O H N T O C Z E K
Good Burger
Item
Sodium
(mg) Fat (g) Calories
Item cost
($)
Beef Patty 50 17 220 $0.25
Bun 330 9 260 $0.15
Cheese 310 6 70 $0.10
Onions 1 2 10 $0.09
Pickles 260 0 5 $0.03
Lettuce 3 0 4 $0.04
Ketchup 160 0 20 $0.02
Tomato 3 0 9 $0.04
As the owner of a fast food restaurant with declining sales, your customers are looking for something
new and exciting on the menu. Your market research indicates that they want a burger that is loaded
with everything as long as it meets certain health requirements. Money is no object to them.
The ingredient list in the table shows what is available to include on the burger. You must include at
least one of each item and no more than five of each item. You must use whole items (for example, no
half servings of cheese). The final burger must contain less than 3000 mg of sodium, less than 150
grams of fat, and less than 3000 calories.
To maintain certain taste quality standards you’ll need to keep the servings of ketchup and lettuce the
same. Also, you’ll need to keep the servings of pickles and tomatoes the same.
Question: What is the most expensive burger you can make?
Send your answer to [email protected] by October 15
th
, 2014. The winner, chosen randomly from
correct answers, will receive a $25 Amazon Gift Card. Past questions can be found at puzzlor.com.
John Toczek is the Sr. Director of Decision Support and Analytics for Aramark Corporation in the Global Operational Excellence
group. He earned his BSc. in Chemical Engineering at Drexel University (1996) and his MSc. in Operations Research from
Virginia Commonwealth University (2005).
pXX OR/MS TODAY and Analytics Magazine August 2014 v1
The PuzzlOR Thinking Analytically
26
72
DEPARTMENTS
2 Inside Story
8 Executive Edge
12 Analyze This!
18 INFORMS Initiatives
24 Forum
26 Healthcare Analytics
62 Conference Preview
68 Five-Minute Analyst
72 Thinking Analytically
Tel 775 831 0300 • Fax 775 831 0314 • [email protected]
ANALYTIC SOLVER PLATFORM
Easy to Use, Industrial Strength Predictive Analytics in Excel
How can you get results quickly for business decisions,
without a huge budget for “enterprise analytcs”
sofware, and months of learning tme? Here’s how:
Analytc Solver Platorm does it all in Microsof Excel,
accessing data from PowerPivot and SQL databases.
Sophistcated Data Mining and Predictve Analytcs
Go far beyond other statstcs and forecastng add-ins
for Excel. Use classical multple regression, exponental
smoothing, and ARIMA models, but go further with
regression trees, k-nearest neighbors, and neural
networks for predicton, discriminant analysis, logistc
regression, k-nearest neighbors, classifcaton trees,
naïve Bayes and neural nets for classifcaton, and
associaton rules for afnity (“market basket”) analysis.
Use principal components, k-means clustering, and
hierarchical clustering to simplify and cluster your data.
Simulaton, Optmizaton and Prescriptve Analytcs
Analytc Solver Platorm also includes decision trees,
Monte Carlo simulaton, and powerful conventonal and
stochastc optmizaton for prescriptve analytcs.
Help and Support to Get You Started
Analytc Solver Platorm can help you learn while
getng results in business analytcs, with its Guided
Mode and Constraint Wizard for optmizaton, and
Distributon Wizard for simulaton. You’ll beneft from
User Guides, Help, 30 datasets, 90 sample models, and
new textbooks supportng Analytc Solver Platorm.
Surprising Performance on Large Datasets
Excel’s ease of use won’t limit what you can do – Analytc
Solver Platorm’s fast, accurate algorithms rival the
best-known statstcal sofware packages.
Find Out More, Download Your Free Trial Now
Visit www.solver.com to learn more, register and
download a free trial – or email or call us today.
WWW. I NF OR MS . OR G 8 | A NA LY T I CS - MAGA Z I NE . OR G
One of the most overused words of the last decade
is “innovation.” As with most buzzwords, the more it’s
used, the less it tends to mean. But real innovation
is what determines progress, and often as a result
of progress, the defnition of innovation changes with
time. So, what does innovation mean now?
First, let’s look at what it meant back in the day.
Innovation meant taking risks, betting on something
new. Today’s innovators likely still are risk takers –
that, after all, is the nature of business. But we’ve
advanced since then. Now, to cultivate and sustain
success, the risk takers must also be risk mitigators.
Today, taking risks and innovating go beyond in-
vesting in technology. Innovation is about investing
in new ways of thinking and empowering people to
challenge the status quo – whether to create a new
product, fnd an unconventional solution or anticipate
opportunities. One example that meets all those crite-
ria is today’s mesh economy – companies that invent
new ways for people to share products and servic-
es, driving traditional companies to rethink their ap-
proaches to innovation.
Innovation is about
investing in new
ways of thinking and
empowering people to
challenge the status quo.
BY SCOTT STEPHENSON
Innovation redefined:
beyond investing in
technology
EXECUTI VE EDGE
Tel 775 831 0300 • Fax 775 831 0314 • [email protected]
ANALYTIC SOLVER PLATFORM
From Solver to Full-Power Business Analytics in Excel
The Excel Solver’s Big Brother Has Everything You
Need for Predictve and Prescriptve Analytcs
From the developers of the Excel Solver, Analytc Solver
Platorm makes the world’s best optmizaton sofware
accessible in Excel. Solve your existng models faster,
scale up to large size, and solve new kinds of problems.
From Linear Programming to Stochastc Optmizaton
Fast linear, quadratc and mixed-integer programming is
just the startng point in Analytc Solver Platorm. Conic,
nonlinear, non-smooth and global optmizaton are just
the next step. Easily incorporate uncertainty and solve
with simulaton optmizaton, stochastc programming,
and robust optmizaton – all at your fngertps.
Ultra-Fast Monte Carlo Simulaton and Decision Trees
Analytc Solver Platorm is also a full-power tool for
Monte Carlo simulaton and decision analysis, with a
Distributon Wizard, 50 distributons, 30 statstcs and
risk measures, and a wide array of charts and graphs.
Comprehensive Forecastng and Data Mining
Analytc Solver Platorm samples data from Excel,
PowerPivot, and SQL databases for forecastng and data
mining, from tme series methods to classifcaton and
regression trees, neural networks and associaton rules.
And you can use visual data exploraton, cluster analysis
and mining on your Monte Carlo simulaton results.
Find Out More, Download Your Free Trial Now
Analytc Solver Platorm comes with Wizards, Help, User
Guides, 90 examples, and unique Actve Support that
brings live assistance to you right inside Microsof Excel.
Visit www.solver.com to learn more, register and
download a free trial – or email or call us today.
WWW. I NF OR MS . OR G 10 | A NA LY T I CS - MAGA Z I NE . OR G
EXECUTI VE EDGE
THREE KINDS OF INNOVATION
The Verisk Analytics innovation model
consists of three subsets:
• process innovation – drives effciencies
in business operations
• product innovation – extends existing
products with new functionality and
capabilities
• invention – redefnes markets and
creates new industry ideas
We implement all three, with an empha-
sis on invention. Invention stems from our
collaboration with customers, allowing us
to gain a thorough understanding of what
challenges confront the markets we serve
and how we can fnd solutions to those is-
sues. Equally, collaboration with our cus-
tomers enables us to discover what works
well and where the growth opportunities
exist for them – and, consequently, what
services we need to create, revive, or ex-
pand to meet their growing requirements.
With customers deeply involved in our
development process, we gain the beneft
of real-time insights and reactions as they
move through phases of innovation with
us – from ideation to prototype to adoption.
That kind of collaboration has redefned
what innovation truly means today both at
Verisk and for many other organizations.
INNOVATION: WHAT’S NEXT?
Investing in innovation requires a
culture that supports innovation, ensuring
employees understand and rally around
an organizational philosophy defning what
innovation means and why it matters. The
Verisk concept of innovation is based on
our n+1 philosophy: To be competitive to-
day, organizations must strive for what we
call the n+1 data set. If a company’s data
set has a certain number of elements —
n — it must constantly be working to in-
clude one more. It must continually add
elements, advancing toward the next layer,
adding richness to its analysis. To be sure,
such an approach requires investment – in
data resources, in analytics, in technology,
in people. But the return on investment is
to thrive, rather than simply survive or ulti-
mately fail. That’s true for all industries but
especially so in data-driven industries such
as insurance, healthcare and supply chain,
among others.
The n+1 philosophy can help a com-
pany answer such crucial questions as,
What’s next? and What should we do to
improve effciency, reduce risk, indeed
turn risk into opportunity and increase
growth?
For example, a comprehensive supply
chain risk management strategy – along
with the incorporation of an array of pre-
dictive analytic tools to measure and man-
age risk – often extends beyond the supply
chain itself to encompass all major opera-
tions of the organization. In fact, modern
predictive analytics is fast becoming a
tool to recognize key trends, patterns and
potential disruptions within supply chains.
It’s a means to protect the enterprise’s
most valuable assets while also creating
sophisticated risk resilience and mitiga-
tion models.
EXPONENTIAL BENEFITS
A recent PricewaterhouseCoopers sur-
vey indicates that over the next fve years,
the most innovative companies are set to
grow at twice the pace of the global aver-
age and three times the rate of the least
innovative.
There’s a myriad of literature available
about innovation, yet much is not particu-
larly helpful because it tends to describe
innovation as a single element. Quite the
contrary, there are several different modes
of innovation, and a company has to be
clear about what it means when using the
term. What kind of innovation is the com-
pany looking for?
Innovation through the n+1 philoso-
phy shows up everywhere in the form
of this question: Is there a layer of data
we’re not yet accessing that may drive us
toward a better solution? One example
can be found in catastrophe modeling.
Historically, our business has tried to un-
derstand the probability of a range of per-
ils, such as hurricanes. Companies need
to understand both a hurricane’s location
and intensity. But we’re also aware there
have been changes in the composition of
the atmosphere that potentially can lead
to an extreme weather event, such as a
hurricane. That said, if the temperature of
the surface of the ocean correlates with
the amount of energy that can affect the
next hurricane developing at sea, a com-
pany can use new parameters, such as
sea surface temperatures, in its analysis.
That’s the +1 layer. And each layer can
set the stage for yet another.
So, meaningful innovation today ap-
plies n+1 as its foundation and embraces
a comprehensive dialog with customers
to make sure a company truly under-
stands its customers’ emerging needs.
From the strength of that relationship, a
business tends to realize a viable prod-
uct and associated revenue much faster.
And the benefts just accrue from there:
Rather than aiming to build the solution
of all solutions, a business can produce
more refned iterations – one at a time –
and then enjoy the rewards of one suc-
cess after another. ❙
Scott Stephenson is president and chief executive
offcer of Verisk Analytics.
Subscribe to Analytics
It’s fast, it’s easy and it’s FREE!
Just visit: http://analytics.informs.org/
S E P T E MB E R / OCT OB E R 2014 | 11 A NA L Y T I C S
WWW. I NF OR MS . OR G 12 | A NA LY T I CS - MAGA Z I NE . OR G
ANALYZE THI S!
As I write this, I am as usual frantically prepar-
ing for the new school year, which starts in just a
few short days. I am once again teaching exclusively
MBA students here at the University of San Fran-
cisco. This year, in addition to the core quantita-
tive methods course and my longstanding applied
statistics elective, I’m also teaching a new elective
entitled “Introduction to Data Mining.”
All of our analytics courses for MBA students
are taught with a strong practical bent. Our core
MBA course is entitled “Spreadsheets and Business
Analytics,” and not surprisingly this course requires
students to be very hands-on with Excel in building
models and analyzing historical data. In addition,
because both of my electives for this fall place a
heavy emphasis on data analysis, both of them are
built around the JMP software from SAS Institute.
At this point, a short digression for a true con-
fession: I have never liked computer programming.
It’s not that I’m not capable of doing this kind of
work – just ask me about the integration of GAMS
with Mathematica in order to run numerical experi-
ments for my dissertation! – but the reality is that
programming is something that I do not for the most
Students, professionals need
‘data wrangling’ skills
BY VIJAY MEHROTRA
It seems irresponsible
of business schools to
continue to teach a core
curriculum that does not
reflect the increasingly
central role of software
programming.
A NA L Y T I C S
part enjoy. In my research, I am always
looking for existing software tools (or
graduate students) that I might be able
to deploy to get my experiments done
more quickly, and I will invariably write
code from scratch only as a last resort.
Given this aversion to programming,
I am able to empathize with my MBA
students, the vast majority of whom
have little or no background with coding.
Moreover, all of the same factors that
have driven the proliferation of analytics
in the business world have also made it
possible – and increasingly easier – for
me to teach a lot of relatively sophisticat-
ed mathematical and statistical applica-
tions to these students. So I am thrilled
that thanks to today’s faster hardware
and user-friendly software, I can bring
some important ideas and techniques to
my MBA students in a hands-on way.
A select few of my MBA students
ultimately decide to take my “Analyt-
ics Consulting Projects” course [1], and
that’s where the game changes radical-
ly. The reality is that there is virtually no
S E P T E MB E R / OCT OB E R 2014 | 13
See how industry leaders use AnyLogic
Network with globally recognized organizations
Experience solutions and the logic behind them
Immediately following INFORMS Annual Meeting
Supply Chain & Logistics
Warehouse & Distribution
Presenting Organizations include ...
Healthcare • Business Process • Pedestrian Flow • Rail • Marketing •
Finance • Military & Defense • Supply Chain • Logistics • Distribution
Scan to register
to solve real world business problems
WWW. I NF OR MS . OR G 14 | A NA LY T I CS - MAGA Z I NE . OR G
ANALYZE THI S!
way to do a meaningful real-world analytics proj-
ect without doing a signifcant amount of data
manipulation work to get the data into shape
for whatever analysis needs to be done. As the
New York Times’ Steve Lohr recently reported
[2], this need for extensive “data wrangling” is as
great for professional data science teams as it is
for my students.
This is where the fun begins. How do you
manipulate data without writing a computer pro-
gram? The most common frst step is to use
Excel to manipulate raw data into the required
format, often in awkward and unnatural ways.
This is not only because of Excel’s increasingly
powerful capabilities for sorting, searching and
summarizing but also because this is an envi-
ronment with which they already have extensive
experience and comfort. One of last year’s proj-
ect teams, upon fnally determining a particular
statistical analysis that would provide the client
with some unique insights, spent several hours
perusing and posting on http://www.mrexcel.
com/ before ultimately fguring out how to do the
lookup/summary calculations that were needed
to prepare the data.
As the limitations of the Excel platform be-
come apparent, some teams have no choice
but to get educated on other tools such as Py-
thon, SQL and R. In class, we often hold short
workshops to help support this learning process,
some led by me and others organized by the
students. But all of this consumes valuable time
on the project calendars, and this data wran-
gling is often the source of a great deal of stress,
All of the students learn
that these capabilities are
truly essential in order
for them to be able to
answer even moderately
challenging business
questions whose answers
are data-driven.
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 15
especially since the problem statement
and solution methodology is also evolv-
ing along the way for most projects.
All of the students in this projects
course ultimately learn that these ca-
pabilities are truly essential in order for
them to be able to answer even mod-
erately challenging business ques-
tions whose answers are data-driven.
As such, after teaching this class for a
second time last spring, I began thinking
that a programming prerequisite might
be worth creating. The course that I had
envisioned would be ruthlessly practical
(fundamental programming logic, basics
of relational databases and SQL, and ex-
amples of how to manipulate data in a few
different environments including Python,
SAS, SPSS and R). The goal would be
to give them a little more skill – and a lot
more confdence – in their ability to man-
age the data on subsequent projects.
It turns out that I’m not the only busi-
ness faculty member thinking about
Position yourself in a lucrative new career
with a master’s degree in Business Analytics or Supply Chain Management.
Stand Out.
Be Boulder.
Get started now: www.leeds.colorado.edu/MS
Leeds alum Matt Emmi,
founder of OneButton,
Boulder-based tech company
Intensive nine month programs
World-renowned faculty
Experiential projects with industry clients
Personalized professional development
12-6 leeds ad alternate_Layout 1 12/20/13 8:13 AM Page 1
WWW. I NF OR MS . OR G 16 | A NA LY T I CS - MAGA Z I NE . OR G
ANALYZE THI S!
whether my students should learn to
write code. A recent Business Week ar-
ticle entitled “B-Schools Finally Acknowl-
edge: Companies Want MBAs Who Can
Code” [3] provides a brief description of
what several elite MBA programs are do-
ing to provide their students with opportu-
nities to study programming. Yet almost
none of the examples that are cited in
the article, ranging from a joint MBA and
MS in computer science at Stanford to
new elective courses being considered
at Harvard, mention data management
(with the exception of economist David
Backus’ new elective in data visualiza-
tion and Python being offered at NYU
starting this fall). Instead, the focus of
the article is on MBAs who want to pur-
sue careers as product managers and
tech entrepreneurs and what these elite
programs are doing to support them.
I would argue that there is something
more profound here for business schools
to consider. As Marc Andreessen famously
pointed out in 2011, “More and more major
businesses and industries are being run
on software and delivered as online servic-
es – from movies to agriculture to national
defense. …Six decades into the computer
Join the Analytics Section of INFORMS
For more information, visit:
http://www.informs.org/Community/Analytics/Membership
NOTES & REFERENCES
1. http://www.analytics-magazine.org/may-june-
2013/798-analyze-this-course-puts-students-in-the-
analytics-game
2. For the complete article, see http://www.nytimes.
com/2014/08/18/technology/for-big-data-scientists-
hurdle-to-insights-is-janitor-work.html?_r=0
3. http://www.businessweek.com/articles/2014-07-11/b-
schools-fnally-acknowledge-companies-want-mbas-
who-can-code
revolution, four decades since the inven-
tion of the microprocessor and two decades
into the rise of the modern Internet, all of
the technology required to transform in-
dustries through software fnally works …”
In light of this reality, it seems irresponsible
of business schools to continue to teach
a core curriculum that largely does not re-
fect this increasingly central role.
While a class or two in software
programming will not solve that problem
overnight, it is certainly a start. And any
class that helps us create graduates that
can wrangle a lot more of their own data
should also be a big plus for our quanti-
tatively oriented MBA students – and for
their future employers.
Vijay Mehrotra ([email protected]) is a
professor in the Department of Business Analytics
and Information Systems at the University of San
Francisco’s School of Management. He is also a
longtime member of INFORMS.
© 2014 Fair Isaac Corporation. All rights reserved.
Now part of FICO
®
Xpress
Optimization Suite.
Parallel
Simplex
S
1
X
1
X
2
X
3
S
1
S
2
P
S
1
P
People have been attempting to add parallel processing to the simplex method for linear programming for well
over 30 years. FICO is proud to announce that we have solved this enormously difcult problem and can now ofer
parallel simplex in our software, including FICO® Xpress Optimization Suite.
The addition of parallel processing to simplex algorithms speeds performance of FICO® Xpress Optimization Suite
by as much as a factor of 2.5.
Our method for the parallelization of classic simplex algorithms involves picking apart the
algorithmic components and rearranging them to make the algorithm open to parallelization.
Learn more about parallel simplex and FICO
®
Xpress Optimization Suite:
http://www.fico.com/xpress
WWW. I NF OR MS . OR G 18 | A NA LY T I CS - MAGA Z I NE . OR G
The Sears, Roebuck and Co. catalog once offered
customers products in three tiers of quality: “good,”
“better” and “best.” The price for each product corre-
sponded to distinguishing features that made choices
good, and others still better or best. It was an elegant
solution for simpler times. These paper catalogs pro-
vided customers with an information model for pru-
dent investments in products such as a pair of boots
– ftting customers both literally and fguratively ac-
cording to their needs, resources and size.
The INFORMS Analytics Maturity Model or IAMM
(see earlier articles in OR/MS Today [1] and in Analytics
magazine [2]) is now available in a beta version (https://
analyticsmaturity.informs.org/). It emulates these
“good,” “better” and “best” principles in two ways.
First, the fervor of big data and business analyt-
ics have led to a bumper crop of competing analytics
maturity models that can be characterized as “home-
grown or proprietary” (good), “scholarly” (better) and
“impartially developed by a respected panel of ex-
perts” (best) solutions. As the largest nonproft associ-
ation of analytics professionals with 11,000 members
from across academia, business and government,
INFORMS is uniquely qualifed and positioned to
An analytics maturity
model that fits
BY AARON BURCIAGA, CAP
The fervor of big data
and business analytics
have led to a bumper crop
of competing analytics
maturity models that can
be characterized as good,
better and best.
I NFORMS I NI TI ATI VES
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 19
defne the new standard. Moreover, use
of the IAMM is free; it is not associated
with any commercial software or service.
The second way in which the IAMM
is reminiscent of Sears, Roebuck and
Co. catalogs is that it effciently organiz-
es information to ft solutions to custom-
er needs, resources and size. One size
does not ft all. Thus, IAMM guides you,
the user, toward developing an appro-
priately scaled analytics program mak-
ing right-sized investment(s). During
your assessment, the IAMM will guide
you through a process to score analytic
maturity in three crucial areas: 1) orga-
nization, 2) analytics capability and 3)
data & infrastructure. Each one of these
three themes is further defned by the
four factors shown in Figure 1.
In the spirit of TurboTax, WebMD and
other award-winning applications, the
IAMM asks you to answer 12 fundamen-
tal questions about your use of analytics.
Scores are entered on a 10-point scale
that identifes beginning, developing and
advanced analytics maturity. You can
then view your scorecard along with an
important beneft: customized recom-
mendations, along with the ability to set
goals, build a plan to incrementally de-
velop the analytics maturity score and
track progress over time.
For example, you may fnd you are a
3/“beginner” in a category today. Using
linked services, benchmarks and best
practices, you can determine how and
when you can achieve a 7/advanced
level. This goal-setting feature identifes
what specifc actions, policies or invest-
ments are necessary to reach that level
Figure 1: IAMM themes and factors.
WWW. I NF OR MS . OR G 20 | A NA LY T I CS - MAGA Z I NE . OR G
I NFORMS I NI TI ATI VES
of analytic maturity. It helps you, your cli-
ents and your executives to: 1) Develop
and execute action plans; 2) justify re-
source investments; and 3) target key ar-
eas within the business.
You will notice that context for each of
your “as-is” and “to-be” scores is enriched
by the benchmark information provided
according to your industry – baselines by
which you can compare your business’
current and goal states against other
similar businesses. This unique feature
of the IAMM helps you create or maintain
a competitive advantage and provides
both the rationale and justifcation for
investments.
If you need assistance developing
your plan and improving your organiza-
tion’s use of analytics, you can follow links
to INFORMS services that can help you in
the areas that are most important to you.
The committee has received ques-
tions about the security of data input by
users. The INFORMS IT department dou-
ble encrypts the data to protect users’ pri-
vacy. No proprietary data is shared.
IAMM celebrated its soft launch at the
INFORMS Big Data Conference in San
Jose, Calif., in June. INFORMS IT Direc-
tor Nagaraj Reddi and I unveiled it for the
many participants who turned to INFORMS
for expertise in analytics.
An active team of INFORMS practi-
tioners from respected frms has been
developing the IAMM for two years, care-
fully determining the needs of users and
noting the INFORMS model’s unique po-
sition vis-à-vis other models. The IAMM
Committee is chaired by Norm Reitter
of CANA Advisors and includes, Rob
Benson (Spinaker), John Poppelaars
(ORTEC), Jim Williams (FICO) and Aar-
on Burciaga (Accenture), with INFORMS
staffng by Executive Director Melissa
Moore, Communications Director Barry
List and IT Director Nagaraj Reddi.
Just as Sears, Roebuck and Co. cata-
logs once met customer needs with tiered
products, the INFORMS IAMM provides
tailored assessments and solutions for
right-sizing an analytics program. Com-
plete your assessment today, ftting you
and your business to good, better or best
options for analytics maturity at https://
analyticsmaturity.informs.org/. ❙
Aaron Burciaga, CAP, is senior manager, analytics
and operations research, at Accenture. Barry List,
INFORMS director of communications, contributed
to this article.
NOTES & REFERENCES
1. Reitter, Norman, and List, Barry, 2013, “Analytics
Maturity Model,” OR/MS Today, Vol. 40. No. 5 (October
2013). Available online at: https://www.informs.org/
ORMS-Today/Public-Articles/October-Volume-40-
Number-5/INFORMS-NEWS-Analytics-Maturity-Model
2. 1. Reitter, N., and List, B., 2013, “INFORMS Analytics
Maturity Model,” (November/December 2013).
Available online at: http://www.analytics-magazine.
org/november-december-2013/904-informs-analytics-
maturity-model
career analytics.
Enroll now only
AAS
nation.
Wake Technical Community College served
68,919 students in 2012-13 and was
ranked the second largest community
college in the country in 2012 by
Community College Week.
A future forward college, it launched the AAS
in Business Analytics, the first of its kind, in
2013. The program provides students the
knowledge and practical skills necessary for
employment and growth in analytics
professions in as little as two semesters.
Competitive tuition, open-door enrollment,
flexible scheduling options, access to industry
recognized tools, and a variety of credential
options make enrollment in the program
both accessible and affordable.
This program is funded in full by a $2.9 million
Dept. of Labor Trade Adjustment
Assistance Community College & Career
Flexibility
Credential
Options
Executive
Accelerated
Program
Industry
Recognized
Tools & Skills
WWW. I NF OR MS . OR G 22 | A NA LY T I CS - MAGA Z I NE . OR G
I NFORMS I NI TI ATI VES
INFORMS’ Certifed Analytics Profes-
sional (CAP
®
) program was recently listed
frst by CIO magazine among the “11 Big
Data Certifcations That Will Pay Off.” Cre-
ated by the largest society in the world for
professionals in the felds of analytics, op-
erations research and management sci-
ence, INFORMS’ CAP exam is given at
hundreds of computer-based testing cen-
ters worldwide through an agreement with
Kryterion (a full-service provider of cus-
tomizable assessment and certifcation
products and services).
Eligible candidates for the CAP certi-
fcation exam can now choose to sched-
ule their exam through INFORMS’ online
testing center partner Kryterion, as well
as strategic partnerships with colleges
and universities and testing and training
companies. Kryterion provides more than
700 testing locations (including 400 in the
United States) in more than 100 coun-
tries. CAP exams can now be scheduled
almost any day of the week and at a time
and location that best suits the candidate.
Exam locations can be found at http://
www.kryteriononline.com/host_locations/.
Introduced in the spring of 2013, the
CAP program was created by subject
matter experts, many of whom are IN-
FORMS members. The CAP credential
is designed for general analytics profes-
sionals in early- to mid-career. The exam
is based on a rigorous job task analysis,
and it is vendor- and software-neutral.
Candidates can apply at www.informs.
org/applyforcertifcation. Upon payment,
eligible candidates receive an online
voucher to present on the Kryterion site.
Benefts of analytics certifcation in-
clude the ability to advance one’s career
by self-identifying as a professional that
sets you apart from the competition, as
well as a strong sense of satisfaction in
earning an industry developed creden-
tial. The CAP designation demonstrates
a continuing commitment to maintain
or increase one’s level of knowledge
through a mandatory continuing educa-
tion obligation.
CIO Magazine:
INFORMS’ CAP program
‘pays off’
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 23
The CAP program assists hiring
managers in selecting analytics talent,
and it shows that an organization hiring
CAP professionals follows best analytics
practice.
The following individuals received CAP
certifcation during the frst half of 2014:
Brian Backer, Johns Creek, Ga.
A. Dwayne Ball, Lincoln, Neb.
Eriketa Bakiri, Cincinnati
Mehmet Begen, London, Ontario
William Bentley, Alpharetta, Ga.
David M. Blum, Arlington, Va.
Brad Boehmke, Dayton, Ohio
Alan Briggs, Odenton, Md.
Aaron Burciaga, Fairfax, Va.
Charles Burdick, Silver Spring, Md.
Fernanda Maria Campello de Souza,
Edmonton, Alberta
Ibrahim Capar, Tuscaloosa, Ala.
Andrew Churchill, Poolesville, Md.
Kelly Cormican, Virginia Beach, Va.
Elizabeth Dalton, Liberty Township,
Ohio
Chao Deng, Morrisville, N.C.
Shannon Downs, Loveland, Ohio
David Durkin, Roswell, Ga.
Krista Elefante, Reston, Va.
Rachel Ferst, San Mateo, Calif.
Michele Fisher, Park South, South Africa
Daniel Ford, Bethesda, Md.
Nick Freeman, Tuscaloosa, Ala.
Peter Furseth, Dallas, Texas
Mark Gallagher, Fredericksburg, Va.
Ira Gershkoff, Ashburn, Va.
Nathaniel Givens, Williamsburg, Va.
Jessica Guo, Portland, Ore.
Brian Harris, Alexandria, Va.
Daniel Hudson, Hanover, Md.
Stephen E. Hunt, Jr., Sumter, S.C.
Alev Kaya, Summit, N.J.
Dong-Gook Kim, Dalton, Ga.
Andrew Kuoh, Washington, D.C.
Jon Kidder, Mount Pleasant, S.C.
Andrew Kiekhaefer, Coralville, Iowa
David Krahl, San Jose, Calif.
Robert Liebe, Stafford, Va.
Michael Maguire, Washington, D.C.
Craig Maxey, South Riding, Va.
James Muccio, Fairfax, Va.
David Munoz, Mexico D.F., Mexico
Joseph Olah, Elkton, Md.
Jonathan Owen, Beverly Hills, Mich.
Sung-Hee Park, Dalton, Ga.
Johann Pasion, Manchester, N.H.
Jesse Pietz, Monument, Colo.
Christopher Provan, Springfeld, Va.
Scott Radcliffe, Roswell, Ga.
Nishit Shah, Maple, Ontario
Scott Smith, Arlington, Mass.
Wei Song, Mississauga, Ontario
Jason Southerland, Fort Belvoir, Va.
Eric Stephens, Nashville, Tenn.
James Stone, Reading, Mass.
Brando Sumayao, Chula Vista, Calif.
Matthew Wagner, Silver Spring, Md.
Rodney Zwainz, Crofton, Md.
WWW. I NF OR MS . OR G 24 | A NA LY T I CS - MAGA Z I NE . OR G
As we look at the growing feld of analytics, it’s
pretty clear that it can provide the signposts to help or-
ganizations gauge how well they are doing. In speak-
ing about signposts, this reminds me of one of my
pet peeves over the years – lack of proper signage,
especially at airports. Nothing can be more frustrating
than not fnding your way to and within the airport.
Case in point: Traveling from Montreal to the
Burlington, Vt., airport, a sign says, “New York or
Vermont.” If you follow the Vermont sign, which would
be the most natural choice, it takes you all around the
state of Vermont, and you’ll never make your fight out
of Burlington (I know, it is the only fight I have ever
missed in all my years of fying).
It is even more annoying to follow signs at the air-
port that are blurred. That’s right, according to Alice
Rawsthorn’s 2012 New York Times article, “Design-
ers of the Signs that Guide You,” the new signs in the
Vienna Airport are intentionally blurred. This can be
troublesome for those who might have jet lag and
haven’t slept well on the plane, aside from those who
are vision impaired.
Airport signage needs to be clear, concise and
minimize customer dissatisfaction. Some airports are
getting better with their signage. Instead of saying
“Arrivals” and “Departures,” some say “Ticketing/
Signs point to what
analytics still needs
BY JAY LIEBOWITZ
Analytics need to convey
and capture the right
measures, such as key
performance indicators
in the organization’s
executive dashboards.
If you don’t know where you are going, any road will take you there.
FORUM
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 25
Check-in” and “Passenger Pick-up.”
However, some airports like Brussels,
Belgium, are still using Helvetica type
which is one of the poorest fonts for read-
ability. And, with car rental return signs,
drivers are still being confused at such
airports in Orlando, Fla., and Florence,
Italy, according to the blogs and newspa-
per accounts.
In the same manner, analytics need to
convey and capture the right measures,
such as key performance indicators in
the organization’s executive dashboards.
It needs to not only report on what has
happened (descriptive analytics), but
also what will happen (predictive ana-
lytics) and ultimately what are the opti-
mal conditions (prescriptive analytics for
optimization).
We can learn what still needs to be
done in analytics by looking at airport sig-
nage to increase customer satisfaction.
First, don’t get fancy with the airport sig-
nage – people want to be able to recog-
nize the signs quickly (whether driving or
catching fights in the airport). The signs
need to clearly communicate the intent,
both visually and content-wise. In much
the same way, analytics should use the
KISS philosophy (keep it simple, stupid)
and provide the appropriate messages
and signals.
Second, design signs with the lowest
common denominator in mind. That is, as
international and domestic visitors trav-
el throughout airports, include universal
symbols, colors and verbiage so that the
typical traveler can understand. Analytics
can also use this guidance in terms of their
respective end users.
Finally, continue to embed an analyt-
ics culture throughout the organization in
the same way that airport signs should
also be intuitive.
Similar to using analytics for improv-
ing the business user’s experience, I am
also trying to suggest ways to improve
the airport signage for the average trav-
eler. And, it’s not just in the airline indus-
try; it applies across other transportation
industries as well. For example, I noticed
that there was an electronic sign at the
front of each Amtrak car that stated,
“Exit,” and whether the rest room was
occupied. Why couldn’t the sign also in-
clude the train stop at each embarkation?
Call me crazy, but I’m still “waiting for
a sign.” ❙
Jay Liebowitz ([email protected]) is the
DiSanto Visiting Chair in Applied Business and
Finance at Harrisburg University of Science and
Technology, Harrisburg, Pa. He will be a keynote
speaker at the Analytics Conference 2014 in Las
Vegas on Oct. 20-21.
Help Promote Analytics Magazine
It’s fast and it’s easy! Visit:
http://analytics.informs.org/button.html
WWW. I NF OR MS . OR G 26 | A NA LY T I CS - MAGA Z I NE . OR G
A couple of interesting developments happened
during the past few months. Google launched its next
healthcare initiative, Baseline Study, to do genetic
analysis and determine what a healthy human body
should be [1]. It will start with the genetic and molec-
ular information from 175 volunteers, but it later will
expand into thousands more. Google also announced
its Google Fit platform and launched SDK.
In the electronic medical record (EMR) space,
Cerner, a known behemoth, bought the health IT busi-
ness from Siemens after the latter decided to exit this
vertical. Cerner’s acquisition is an interesting devel-
opment. It shows that the EMR market is opening up
for consolidation. A few large corporations, each with
large market share, will eventually dominate the EMR
marketplace catering to mostly large buyers.
Too many options usually paralyze buying deci-
sions. Apple decided to work closely with IBM to pen-
etrate the enterprise software business. Healthcare
has not been mentioned yet as part of the newly
formed partnership, but this is certainly a possibility.
In my last article, I mentioned how IBM’s strategy of
“Watson in the cloud” for healthcare can receive a
huge boost owing to the overwhelming preference of
clinicians for Apple devices.
The need for not-for-profit
organizations
BY RAJIB GHOSH
It is heart-warming
to see providers and
payers increasingly
focused on health data
and analytics to figure
out better ways to
deliver quality care
without increasing cost.
TRUTHS & FUNDAMENTALS
J U LY / AU GU S T 2014 | 27 A NA L Y T I C S
INVESTMENT INCREASING
Investment in digital health technolo-
gies is also increasing at an unprecedented
rate. It is heart-warming to see that pro-
viders and payers alike are becoming
increasingly focused on health data and
analytics to fgure out better ways to de-
liver quality care for patients without in-
creasing cost. Interestingly, this trend is
not limited to the for-proft business world.
Not-for-proft health plans, managed
care businesses and community-based
healthcare providers are also paying atten-
tion to the data that they have and analytics
they need to become effcient in care deliv-
ery in the post Affordable Care Act (ACA)
world. While challenges and jubilations in
the for-proft healthcare organizations be-
come newsworthy, data and analytics effort
of the not-for-proft community healthcare
providers seldom make the news. This ar-
ticle focuses on the latter – primarily com-
munity-based healthcare clinics, hospitals
and managed care organizations – that
serve a large Medicaid population that is
generally poor, underserved or both.
DEMAND GROWING BUT NOT SUPPLY
ACA has started to have noticeable
impact on the demand side of health-
care services, particularly in states
that participated in the ACA-proposed
Medicaid expansion program. Twen-
ty-six states and Washington, D.C.,
have moved forward with the Medic-
aid expansion, leading to more than
3 million additional enrollees into Medic-
aid plans as of April 2014. Many of the
WWW. I NF OR MS . OR G 28 | A NA LY T I CS - MAGA Z I NE . OR G
HEALTHCARE ANALYTI CS
new enrollees were uninsured or under-
insured earlier, causing high emergency
room and hospitalization costs. According
to projections, more than 15 million eligible
people for Medicaid in participating states
have joined the expansion program.
While the expansion brought in new fed-
eral dollars to the respective state coffers
in support of the safety net expansion, the
key issue is that the growth in demand is not
aptly matched by timely capacity expansion.
An imminent scarcity of primary care provid-
ers in many states poses problems for the
proposed expansion. Even when physicians
are available, competition from for-proft or-
ganizations makes them unaffordable to the
not-for-proft health centers and hospitals.
Additionally, Medicaid reimbursement rates
are much lower than commercial plans, so
specialists are not always willing to accept
Medicaid patients. This creates issues for
not-for-proft health plans in terms of main-
taining a comprehensive provider network
to address gaps in the patient care. ACA
has some provisions to address the reim-
bursement issue, but is that enough?
THE COMPETITIVE
ADVANTAGE DEGREE
St eve B.
Cl ass of ‘ 15
FOR MORE INFORMATION | analytics.tamu.edu
The Texas A&M program gives me the
curriculum I’m looking for, the flexibility to
participate remotely and a top-notch staff
of seasoned professors with loads of
practical experience beyond the university.
EXCERPT FROM CLASS OF 2015 FIRST SEMESTER EVALUATIONS
MASTERS OF SCIENCE ANALYTICS
AT HOUSTON CITYCENTRE OR VIA ONLINE
C
M
Y
CM
MY
CY
CMY
K
Analytics_AD_INFORMS.ai 1 8/12/2014 9:15:05 AM
J U LY / AU GU S T 2014 | 29 A NA L Y T I C S
DESPERATE NEED FOR ANALYTICS
The healthcare industry, both the not-
for-proft and proft worlds, was traditionally
not data- and analytics-driven. However,
as the Medicaid patient population increas-
es by leaps and bounds and commu-
nity healthcare organizations cannot hire
enough physicians to expand capacity, a
precarious situation looms. Demonstrat-
ing quality in care delivery is now critical
for community-based healthcare organiza-
tions to ensure sustained federal funding,
but to do so within the constraints of avail-
able resources it is imperative that they
utilize analytics to move toward population
health management, effcient management
of the high cost multi-chronic patients and
in general take necessary steps toward
improved staff productivity. In absence of
coherent data and adequate analytics sys-
tems, this is turning out to be a monumen-
tal task for many organizations.
The reactive nature of the healthcare
industry is partly to blame for making a dif-
fcult situation worse. Everyone knew that
this wave was coming, yet not enough was
done to prepare. On the positive side, this
has opened up new business opportunities
for healthcare analytics companies who
may consider turning their attention to not-
for-proft segment of the U.S. healthcare in-
dustry, a segment that by 2019 is expected
to address the healthcare needs of more
than 50 million people [2].
The non-proft healthcare segment
also is in immediate need for analytics
that can make sense of clinical, operation-
al and fnancial data to provide descrip-
tive, post-mortem analysis of the current
situation and eventually guide the seg-
ment to maneuver the rough waters of the
post-ACA world. This is a new healthcare
environment that is comprised of an un-
precedented number of patients who are
waiting to be taken care of by a decreas-
ing number of physicians, combined with
funding sources that are under increased
governmental scrutiny today and may not
be available in the future.
Rajib Ghosh ([email protected]) is an
independent consultant and business advisor
with 20 years of technology experience in various
industry verticals where he had senior level
management roles in software engineering,
program management, product management
and business and strategy development. Ghosh
spent a decade in the U.S. healthcare industry
as part of a global ecosystem of medical device
manufacturers, medical software companies and
telehealth and telemedicine solution providers.
He’s held senior positions at Hill-Rom, Solta
Medical and Bosch Healthcare. His recent work
interest includes public health and the feld of
IT-enabled sustainable healthcare delivery in the
United States as well as emerging nations.
Follow Ghosh on twitter @ghosh_r.
NOTES & REFERENCES
1. “Google’s New Moonshot Project: the Human
Body.”
2. Anette L.Gardner, “Maintaining Clinic Financial
Stability: Navigating Change, Leveraging
Opportunities.”
WWW. I NF OR MS . OR G 30 | A NA LY T I CS - MAGA Z I NE . OR G
MYTHS OF ANALYTI CS
ith so much attention given
to analytics and insights
over the past few years, re-
visiting some of the indus-
try’s longstanding myths seems in order.
Whether you work with traditional con-
sumer research methods or emerging
business intelligence techniques, here
are 10 fallacies to keep in mind to make
the most out of your efforts:
1. SCIENTIFIC EVIDENCE IS PROOF
History is full of inaccurate predictions
and once believable theories that turned
out to be wrong. Even Einstein, whose
name is now synonymous with genius,
at one point embraced the now obsolete
static universe model. (Read more.) In
marketing, perhaps no other blunder is
more famous than the New Coke launch
in 1985. Taste tests with close to 200,000
consumers indicated New Coke’s taste
was more popular than the original for-
mula. However, Coca-Cola executives
failed to consider the possibility that the
importance of brand heritage trumped
taste, and eventually the company rein-
troduced the original formula in response
to negative public reaction. (Read more.)
Takeaway: Science has always been
subject to error, requiring an open mind
to alternative possibilities.
10 myths of
analytics and
insights
BY WILL TOWLER
W
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 31
2. KNOWLEDGE IS POWER
In their book, “Big Data: A Revo-
lution That Will Transform How We
Live, Think, And Work,” Viktor Mayer-
Schonberger and Kenneth Cukier con-
tend that it doesn’t matter “why” there’s
correlation, just that there “is” cor-
relation. They provide an example of
greater Pop-Tart sales during storms, a
learning that WalMart has used to bet-
ter merchandize. (Read more.) Accord-
ing to the authors, simply knowing that
Pop-Tart sales are likely to increase is
suffcient and doesn’t necessitate deep-
er investigation into underlying causes.
While there’s no doubt this fnding
has valuable business implications,
relying on correlations alone can limit
broader applications and can even en-
tail risk. Case in point: the 2008 fnancial
crisis. Analysis of AAA rated Collateral-
ized Debt Obligations suggested they
were sound investments (i.e., AAA =
safe), but deeper analysis would have
revealed danger. (Read more.)
Takeaway: As the role of data in de-
cision-making increases, never before
has understanding underlying relation-
ships been more important.
3. CORRELATION MEASURES
RELATIONSHIP STRENGTH
A strong case can be made for ques-
tioning the extent to which correlation
refects a relationship between even
seemingly interdependent variables.
Consider U.S. healthcare expenditures
and deaths from heart disease. Between
1960 and 2010, spending on healthcare
in the United States increased more
Figure 1: Correlations can potentially mask deeper relationships.
WWW. I NF OR MS . OR G 32 | A NA LY T I CS - MAGA Z I NE . OR G
MYTHS OF ANALYTI CS
than seven times after adjusting for infa-
tion. In lockstep, deaths due to heart dis-
ease more than halved, making it easy to
conclude that the two are closely related.
Medical care advances are believed to
have contributed to lower heart disease-
related deaths through improved diag-
nosis and treatment. However, general
lifestyle and diet changes also played
signifcant roles. (Read more.) Further-
more, a review of other chronic disease
trends reveals that some medical condi-
tions, such as diabetes, have worsened
(see Figure 1). There’s also myriad other
factors potentially related to escalating
healthcare costs, such as an aging pop-
ulation, greater administrative expenses
and broader marketing pressures.
For another take on how correla-
tions potentially mask deeper relation-
ships, check out Christopher Knittel and
Aaron Smith’s paper “Ethanol Produc-
tion And Gasoline Prices: A Spurious
Correlation.”
Takeaway: Seriously consider wheth-
er correlation truly refects a relationship
or simply masks the infuence of one or
more hidden intervening variables.
4. RANDOM SAMPLING ENSURES
REPRESENTATION
Unless you’re working with full uni-
verse coverage, some form of sampling
is usually required. And while fantastic
in theory, true randomness is diffcult
to achieve. Transactional data are con-
strained by membership and/or opt-outs;
surveys face non-response; and social
media content is subject to issues relat-
ed to self-reporting. Beyond sampling,
the challenge of unbiased representa-
tion is exacerbated by a number of fac-
tors ranging from human predispositions
to herd mentality.
Sinan Aral wrote a convincing piece
in the MIT Sloan Management Review,
for example, explaining the tendency for
online customer reviews to be abnor-
mally j-shaped rather than bell-curved.
Referencing different studies, Aral ex-
plains how herd mentality can lead to a
disproportionate concentration of posi-
tive ratings skewing online reviews over
short and long terms. (Read more.) It’s
another example of how things aren’t al-
ways what they appear to be.
Takeaway: Accurate representation
without some form of post hoc control is
frequently illusive.
5. PEOPLE ARE RATIONAL
Humans act irrationally. As consum-
ers, we often derive greater satisfaction
from the same item if it costs more (not
less); we let decoy options cause us to
make suboptimal decisions (such as
buying something bigger than we nor-
mally would); and we frequently stick
Is your solver provider
getting in the way
of your success?
we make it easier to achieve
your optimization goals.
At Gurobi,
Gurobi.com +1 713-871-9341 [email protected]
Gurobi Optimizer 5.6
State-of-the-Art Mathematical Programming Solver
Experience state-of-the-art optimization algorithms
backed by industry-leading customer support.
Contact us today to request a FREE
full-featured, unrestricted evaluation license.
Faster solutions with superior
algorithms and powerful tuning
Maximum productivity with flexible
interfaces and modeling language support
Great technical support from
easy-to-reach optimization experts
No surprises with our transparent
pricing and flexible licensing
C
M
Y
CM
MY
CY
CMY
K
ball-maze-final-orms-5.6-eval.pdf 1 7/16/14 2:30 PM
WWW. I NF OR MS . OR G 34 | A NA LY T I CS - MAGA Z I NE . OR G
MYTHS OF ANALYTI CS
to what we’re most familiar with (even
if another choice is better for us). The
popularity of behavioral economics re-
fects a growing interest in tapping irra-
tionality for business and government.
There are still plenty of questions about
how best to merge economics and psy-
chology, but their immutable relationship
beyond traditional utilitarian theory is
without doubt. (Read more.)
Takeaway: Even the tightest models
are fallible due to the unpredictability of
human behavior.
6. RECALL IS A TRUSTED FORM OF
MEMORY
It doesn’t take advanced science to
know that our memories are imperfect,
often causing us to forget information
and events. University of Illinois profes-
sor Brian Gonsalves conducted research
in which he found subjects were able to
recall information correctly only 54 per-
cent of the time after being shown simple
images and descriptions. Gonsalves ex-
plains that some people may remember
the general context of an event, but may
not encode specifc details. (Read more.)
Another study on the effectiveness of dif-
ferent advertising research methodolo-
gies found that less than 70 percent of
respondents were able to accurately re-
call ad exposure. The research also re-
vealed that up to 25 percent of those who
were not shown an ad incorrectly recalled
exposure (see Figure 2). (Read more.)
Figure 2: Not so total recall.
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 35
marketing often track different metrics
reviewed in isolation (e.g., sales might
focus on funnel activities while market-
ing might be more concerned with brand
and campaign assessment). Common
or at least integrated metrics not only
align teams but also ensure what’s be-
ing measured is most relevant.
Strategy and customer experience
consultant Christine Crandell recom-
mends three groups of measures in-
cluding end-to-end conversion, revenue
diversity and outcome proftability. Ac-
cording to Crandell, “While there are
literally hundreds of sales and market-
ing metrics that can be used, it comes
down to (these) three that measure
alignment and frame that all-too critical
joint conversation with sales and mar-
keting about what’s working and what
isn’t.” (Read more.)
Takeaway: Sales and marketing
metrics should be shared or at least
integrated in order to work toward the
same goal and evaluate performance
holistically.
9. SOUND ANALYTICS DRIVE
SOUND DECISION-MAKING
The Corporate Executive Board re-
cently conducted a study of 5,000 em-
ployees at 22 global companies and
found that just over one-third of partici-
pants balance judgment and analysis,
Takeaway: Trusting recall as a re-
search methodology brings with it seri-
ous limitations.
7. YOU CAN’T MANAGE WHAT YOU
CAN’T MEASURE
A century ago Lord Leverholm fa-
mously said, “I know half my advertis-
ing isn’t working, I just don’t know which
half.” The uncertainty that comes with
advertising will probably never go away.
One of the key reasons is the inability
to accurately measure priming, in which
exposure to one stimulus infuences re-
sponse to another. While the extent of
priming is debated, that it exists is not.
Our environment infuences our sub-
consciousness through sights, sounds
and smells. (Read more.) In addition,
the effects of priming can be long-last-
ing, well beyond what one might expect.
(Read more.)
Takeaway: The return on some in-
vestments is not always immediate, of-
ten making short-term measurement a
futile task.
8. SALES AND MARKETING METRICS
ARE DIFFERENT
Sales and marketing share the same
overarching objective of driving proft-
able growth. Having common or at least
integrated key performance indicators
would seem reasonable, but sales and
WWW. I NF OR MS . OR G 36 | A NA LY T I CS - MAGA Z I NE . OR G
MYTHS OF ANALYTI CS
key to effective decision-making. The
other two-thirds either go exclusively
with their gut or trust analysis over judg-
ment. The study highlights the chal-
lenge that even sound insights can have
in driving good decision-making due to
broader organizational issues. Accord-
ing to an accompanying article in the
Harvard Business Review, “At this very
moment, there’s an odds-on chance that
someone in your organization is making
a poor decision on the basis of informa-
tion that was enormously expensive to
collect.” (Read more.)
Takeaway: Quality output is only half
the battle when it comes to impactful an-
alytics and insights. The other half of the
battle lies in an organization’s ability to
take action effectively.
10. GREAT INSIGHTS SELL
THEMSELVES
You conducted a momentous re-
search project or developed a ground-
breaking business intelligence system.
Why wouldn’t your work attract fans and
lead to positive change? Industry track
records, however, suggest most proj-
ects fail to accomplish their goals. (Read
more.) Poor problem defnition and oper-
ational snafus are common challenges.
But even projects with clearly defned
objectives and smooth implementa-
tion can fall short of expectations in the
absence of effective communication and
stakeholder engagement.
According to the Project Manage-
ment Institute, among organizations
considered highly effective communica-
tors, 80 percent of projects meet origi-
nal goals vs. only 52 percent at their
minimally effective counterparts. (Read
more.)
Takeaway: Projects without a well-
crafted stakeholder engagement and
communication plan will likely have little
chance of success from the get-go.
New data sources and diagnostic
capabilities continue to enhance the po-
tential value available through analytics
and insights. However, the longstanding
truths of how to make an impact haven’t
and likely won’t change. The fundamen-
tals of statistics, human nature, stake-
holder engagement and communication
remain the same; and effectively lever-
aging their constructs largely determines
project success.
Will Towler is an analytics and insights consultant
working in the Seattle area, and he has nearly
20 years experience in consumer research and
business intelligence. For more, visit his website:
www.insighttrends.com.
Subscribe to Analytics
It’s fast, it’s easy and it’s FREE!
Just visit: http://analytics.informs.org/
It’s fast, it’s easy and it’s FREE!
Just visit: http://analytics.informs.org/
Opportunity
at your fingertips.
Visual Analytics
The answers you need, the possibilities you seek—they’re
all in your data. SAS helps you quickly see through
the complexity and find hidden patterns, trends, key
relationships and potential outcomes. Then easily share
your insights in dynamic, interactive reports.
Try Visual Analytics and see for yourself
sas.com/VAdemo
SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. ® indicates USA registration. Other brand and product names are trademarks of their respective companies. © 2014 SAS Institute Inc. All rights reserved. S120597US.0214
WWW. I NF OR MS . OR G 38 | A NA LY T I CS - MAGA Z I NE . OR G
REALI ZI NG VALUE
he digital universe is ex-
pected to expand expo-
nentially between 2013
and 2020, from 4.4 trillion
gigabytes to 44 trillion gigabytes [1] a
year, and this massive amount of data
will signifcantly impact global industries.
In nontraditional context, analyzing big
data isn’t about managing more or di-
verse data. Rather it is about asking new
questions, up skilling new capabilities,
building new technological environments
and devising holistic communication
strategies to encompass the nuances as-
sociated with complexities of volumes of
data.
Building a high-
performance big
data analytics
organization
BY (l-r) PRAMOD SINGH,
RITIN MATHUR
AND SRUJANA H.M.
T
“From Twitter feeds to photo streams to RFID pings, the big data universe is
rapidly expanding, providing unprecedented opportunities to understand the present
and peer into the future. Tapping its potential while avoiding its pitfalls doesn’t take
magic; it takes a roadmap.” — Chris Berdik, author of “Mind over Mind”
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 39
Numerous opportunities, as well as
challenges, are associated with big data.
Time savings can be achieved through
real-time monitoring and forecasting of
events that impact either business per-
formance or operation. Signifcant cost
savings over traditional analytical tech-
niques can be achieved by adoption of
big data due to usage of Hadoop clusters.
While companies with business mod-
els predicated on the Internet have been
the pioneers of developing big data ana-
lytics, other frms with more established
non-Internet-based models are also rap-
idly adopting big data analytics practices,
typically in response to consumer and
technology trends. With the emphatic big
data explosion, it becomes imperative for
organizations to assess and adopt big
data analytics practices into their deci-
sion-making process.
BIG DATA TOOLS AND
TECHNOLOGIES
When considering an organization’s
needs for big data tools and technologies, it
June 14 - June 17, 2015
Sheraton Montreal
http://meetings2.informs.org/montreal2015
Abstract Submission
is Now Open!
WWW. I NF OR MS . OR G 40 | A NA LY T I CS - MAGA Z I NE . OR G
HI GH-PERFORMANCE ANALYTI CS ORGANI ZATI ON
is useful to think of them in four dimensions.
1. Structured data management:
Tools for managing high-volume struc-
tured data (for instance, clickstream data
or machine or sensor data) are an impor-
tant part of any big data technology stack.
2. Unstructured data management:
The explosion in data volumes have
been to a large extent a result of the rise
in human information, which is typically
comprised of social media data, videos,
pictures and even text data from custom-
er support logs. Tools and technologies
to manage, analyze and make sense of
this data stream are critical to build under-
standing and to correlate with other forms
of structured data.
3. Analytics environment: Combining
both structured and unstructured data, at
scale, requires specialized tools and tech-
nologies to be able to merge these data
sets and to be able to run analytical algo-
rithms. Concepts such as in-database and
in-memory analytics have greatly enhanced
the ability to use large data sets for analysis
at near real-time speeds and to combine the
analytics environment within, for example,
structured data management tools.
4. Visualization: Intuitive representa-
tion of data and results of analysis is a
critical fnal component of the big data
technology stack. This furthers the speed
at which results are understood and in-
sights derived. Tools and technologies
that allow for quick drill down, investiga-
tive analysis are now pervasive and eas-
ily integrated into the analytics stack [2].
Most tools designed for data mining
or conventional statistical analysis are not
optimal for large data sets. A common hur-
dle to cross for most analytics organiza-
tions trying to leverage big data analytics
is availability of big data technologies and
platforms. Organizations usually start off
by using open source technologies to gain
experience and expertise. The big data
analytics space, thankfully, provides many
open source options for organizations.
For example, Hadoop is a good start-
ing place for being able to manage large
data at scale. Combining this with NoSQL
databases such as Hbase or MySQL can
provide a good frst step to get a feel for
handling large data sets. Hadoop ecosys-
tem tools like Hive, Pig, Sqoop, etc. allow
data scientists to also get a feel for be-
ing able to query and analyze large data
sets. R is an open source programming
language and software environment de-
signed for statistical computing and visu-
alization [3]. For visualization, tools like
d3.js allow for creative and varied visual-
ization sets to help data scientists present
results in an intuitive way.
The challenge with using open source
technologies though is two-fold. One, in-
tegrating these with a legacy enterprise
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 41
stack is not easy, and most IT organiza-
tions don’t yet allow for easy integration.
This integration quickly becomes critical
when one moves beyond experimen-
tation into solving real-world business
problems that require multi-dimensional
data, some of which might be in legacy
enterprise data warehouse (EDW) envi-
ronments [4]. Second, while strong use
communities around open source tech-
nologies exist, the learning curve could
be longer given the often less than us-
er-friendly nature of these technologies.
Learning on open source requires a cer-
tain level of existing expertise, and begin-
ners may fnd a learning approach based
on open source harder.
INTEGRATED BIG DATA ANALYTICS
PLATFORM
Most analytics for business use cases
rely on bringing together diverse data sets
to analyze. With big data, these data sets
are no longer limited to just structured
data; they increasingly leverage unstruc-
tured data as well. This calls for a big data
BENEFITS OF CERTIFICATION
• Advances your career potential by setting you apart from the competition
• Drives personal satisfaction of accomplishing a key career milestone
• Helps improve your overall job performance by stressing continuing
professional development
• Recognizes that you have invested in your analytics career by pursuing
this rigorous credential
• Boosts your salary potential by being viewed as experienced analytics professional
• Shows competence in the principles and practices of analytics
APPLICATIONS
• Prepare to apply by reviewing Candidate
Handbook & Study Guide Draft
• Arrange now to secure academic transcript
and confirmation of “soft skills” to send
to INFORMS
COMPUTER-BASED TESTING
It is now more convenient than ever to schedule
your CAP exam in more than 700 Kryterion test
centers in more than 100+ countries. To find the
location closest to you, check this site:
www.kryteriononline.com/host_locations/
QUESTIONS? [email protected]
DOMAINS OF ANALYTICS PRACTICE
Domain Description Weight*
Business Problem (Question) Framing
Analytics Problem Framing
Data
Methodology (Approach) Selection
Model Building
Deployment
Life Cycle Management
*Percentage of questions in exam
I
II
III
IV
V
VI
VII
15%
17%
22%
15%
16%
9%
6%
100%
BECOME A CERTIFED ANALYTICS PROFESSIONAL
DON’T BE LEFT BEHIND.
www.informs.org/Build-Your-Career/Analytics-Certification
WWW. I NF OR MS . OR G 42 | A NA LY T I CS - MAGA Z I NE . OR G
HI GH-PERFORMANCE ANALYTI CS ORGANI ZATI ON
environment that allows data scientists to
work seamlessly across data streams.
Using an integrated environment pro-
vides a quicker, more scalable and inte-
grated approach to analytics. This allows
for a user-friendly environment for data
scientists to learn new skills and adapt
to working with and running analytics on
large data sets. HP HAVEn, for example,
brings together Hadoop, Autonomy, Verti-
ca, HP Enterprise Security and any num-
ber of applications.
BUILDING ORGANIZATIONAL SKILLS
Providing for big data technologies and
platforms sets the baseline for an organiza-
tion. What needs to be done next is to have
a focused effort across the organization to
build the skills in these technologies.
In contrast to traditional analytical orga-
nizations, big data organizations need to
augment existing analytical staffs with data
scientists who possess a higher level of
technical capabilities, as well as the ability
to manipulate big data technologies. These
capabilities might include natural language
processing and text mining skills; video,
image and visual analytics experience; as
well as the ability to code in scripting lan-
guages such as Python, Pig and Hivev. A
data scientist in a big data analytics orga-
nization typically needs skills in three core
areas: 1. business intelligence related skills
to get to the data quickly, 2. statistics and
analytical techniques to be able to analyze
and, 3. business skills to be able to interpret
analysis results in business terms.
The time that an analytics organiza-
tion has to respond to a business need
is shrinking. This gives rise to a situation
where you need all three skill sets in one
person, which is hard to fnd.
To guide skill development among the
existing analyst community, HP developed
competency centers aligned to each of the
key technologies – Vertica for structured
data analytics, Autonomy for unstructured
data analytics and Hadoop as a data lake.
The competency centers cater to focused
competency development through collab-
oration, training and live projects. These
competency centers, composed of data
scientists across the organization, created
a skills framework and a big data curricu-
lum to guide the skill development effort.
RE-THINKING BUSINESS ANALYTICS
With the right tools, technologies and
skill sets, an organization’s next step is de-
ploying big data analytics to solve analyt-
ics questions in different application areas.
A challenge some analytics organizations
might have is getting their teams to think
about how big data analytics applies to
their business areas. Given the relative
maturity of analytics solutions across most
domains, teams sometimes have diffculty
in assessing how big data could help.
MASTER OF SCIENCE IN ANALYTICS
• 15-month, full-time, on-campus program
• Integrates data science, information technology and business applications
into three areas of data analysis: predictive (forecasting), descriptive (business
intelligence and data mining) and prescriptive (optimization and simulation)
• Offered by the McCormick School of Engineering and Applied Science
www.analytics.northwestern.edu
MASTER OF SCIENCE IN PREDICTIVE ANALYTICS
• Online, part-time program
• Builds expertise in advanced analytics, data mining, database management,
fnancial analysis, predictive modeling, quantitative reasoning, and web analytics,
as well as advanced communication and leadership
• Offered by Northwestern University School of Professional Studies
877-664-3347 | www.predictive-analytics.northwestern.edu/info
NORTHWESTERN ANALYTICS
As businesses seek to maximize the value of vast new streams of available data,
Northwestern University offers two master’s degree programs in analytics that
prepare students to meet the growing demand for data-driven leadership and
problem solving. Graduates develop a robust technical foundation to guide
data-driven decision making and innovation, as well as the strategic,
communication and management skills that position them for leadership roles
in a wide range of industries and disciplines.
WWW. I NF OR MS . OR G 44 | A NA LY T I CS - MAGA Z I NE . OR G
HI GH-PERFORMANCE ANALYTI CS ORGANI ZATI ON
At HP, our belief is that big data analyt-
ics impacts analytics in two ways: 1. help-
ing answer existing/legacy questions in
newer ways and, 2. addressing a range of
newer questions and decisions organiza-
tions face today.
An example of the existing/legacy
question is the area of segmentation, a
well-understood area in marketing and
customer analytics. The challenge for
most business analytics teams, though,
is to look at segmentation with the fresh
lens of big data analytics: How can big
data help make segmentation better?
Examples of how big data analytics
can help address new questions is per-
haps best exemplifed when considering
either social media analytics or machine/
sensor data analytics. These diverse ar-
eas are important aspects in business de-
cision-making and impact such functions
as marketing, manufacturing, customer
service and R&D. Both require new ana-
lytical approaches to manage the large
streams of data that get generated.
SUMMARY
To realize value from big data analytics,
organizations need to integrate technology,
tools and practices with existing analytics
ecosystems. The choices to make in terms
of which tools to select and which skills to de-
velop need careful consideration and have
a long-term impact on an organization’s
ability to integrate big data analytics.
Analytics organizations should start
by considering four key questions:
1. What technology and tools are
needed?
2. What platform is best for integrating
these technology choices with each other,
as well as with legacy environments?
3. Which skills do we need to develop
and how do we develop them?
4. How do we integrate all of the above
into the business decision-making process?
These questions require senior manage-
ment time and attention. Addressing these
issues comprehensively can reduce the bar-
riers to success for analytics organizations
looking to incorporate big data analytics. ❙
Pramod Singh ([email protected]) is director
of Digital and Big Data Analytics at Hewlett-Packard
(HP) and a member of INFORMS. He has a Ph.D.
in mathematics from the University of Arkansas and
an MBA in marketing. Ritin Mathur (ritin.mathur@
hp.com) is a senior manager of Big Data Analytics
at HP. Srujana H.M. ([email protected]) is a data
scientist working on big data technology platforms
at HP. All three are based in Bangalore, India.
NOTES & REFERENCES
1. Source: http://www.emc.com/about/news/
press/2014/20140409-01.htm
2. “Big Data Meets Big Data Analytics,” white paper,
SAS Institute Inc., 2012.
3. Source: http://www.networkworld.com/article/2289422/
applications/9-open-source-big-data-technologies-to-
watch.html, last accessed on July 3, 2014.
4. Philip Russom, “Big Data Analytics,” TDWI Best
Practices Report, Fourth Quarter, 2011.
5. Thomas H. Davenport and Jill Dyche, “Big Data
in Big Companies,” paper, International Institute of
Analytics, May 2013.
https://analyticsmaturity.informs.org
· Assess the way your organization uses analytics
· Create an improvement plan
· Track your progress
· Tap the resources of the leading professional association for advanced analytics professionals
THE INFORMS DIFFERENCE
· Reputable
· International Leader
· Free Access to INFORMS Analytics Maturity Model
· Resilient Model That Grows to Meet Your Needs
Begin using the beta version of the INFORMS Analytics Maturity Model.
Just go to https://analyticsmaturity.informs.org.
Start today!
For additional information, email [email protected] or call 433-757-3500, ext. 560
ANALYTICS MATURITY MODEL
Introducing the
WWW. I NF OR MS . OR G 46 | A NA LY T I CS - MAGA Z I NE . OR G
SOCI AL MEDI A
Return on investment: Quick wins and fundamental
measures of posts, tweets, blogs, pings and uploads.
ost, tweet, blog, ping and
upload are some of the poi-
gnant actions in the social
media universe. Like, share,
re-tweet, favorite, re-blog and download
are the karmic reactions that help assess
the validity and credibility of your actions
in the same universe. Almost all organiza-
tions these days spend quite a lot of fnan-
cial and human resources to understand
and make sense of their social media ac-
tions, leading to the eventual reactions.
And a surprising 49 percent of CMOs are
unable to quantify social media impact on
their companies.
Facebook Insights, Twitter Analytics,
YouTube Analytics, LinkedIn Analytics
and Pinterest Analytics are some places
that offer their own analytic platforms to
measure your social media karma. But
what should these measures be about?
Let’s look at the fve fundamental mea-
sures that will serve as quick-wins to ana-
lyze your social media karma.
MEASURE 1: THE “WHO” – Who is the
core group of your audience base?
Getting a pulse of your audience and
the crowd that comes looking for you is
always the key. Instead of shooting in the
Five measures of
social media karma
BY KSHIRA SAAGAR
P
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 47
highly concentrated in specifc urban
locations? Or is it a completely different
story? The answer to this question sets
up the base for all forthcoming social
media activities.
Eventual insights from this exercise
should help you do two things: 1) validate
that you are talking to the right crowd of
people at the right places; and 2) com-
prehensively understand the groups of
people you have been ignoring but who
seem to have considerable presence in
your audience base.
dark with broadcasted content, a frm grip
on who your audience is could enable a
very easy way of chalking out content
and tailoring the messages. Facebook
Insights and other social media analytics
platforms provide a complete breakdown
of your follower group in terms of gender,
age and location.
The metric of interest here would be
the population of your audience in each
of these demographic buckets, result-
ing in your eureka moment of social me-
dia. Is your audience young, mobile and
INFORMS Continuing
Education program offers
intensive, two-day in-person
courses providing analytics
professionals with key skills,
tools, and methods that can
be implemented immediately
in their work environment.
These courses will give
participants hands-on
practice in handling real
data types, real business
problems and practical
methods for delivering
business-useful results.
NEW!
INTRODUCTION TO MONTE CARLO
AND DISCRETE-EVENT SIMULATION
Topic areas:
» Monte Carlo Modeling
» Sensitivity Analysis
» Input Modeling
» Output Analysis
This course will be held
Catonsville, MD (INFORMS HQ)
Sep 12-13, 2014
Chicago, IL
Oct 16-17, 2014
Faculty:
Barry G. Lawson, University of Richmond
Lawrence M. Leemis,
The College of William & Mary
COURSES FOR
ANALYTICS
PROFESSIONALS
ducation
c
ontinuing
Learn more about these
courses at:
informs.org/continuinged
NEW!
FOUNDATIONS OF MODERN
PREDICTIVE ANALYTICS
Topic areas:
» Linear Regression
» Regression Trees
» Classification Techniques
» Finding Patterns
This course will be held
Washington, DC – Sep 15-16, 2014
San Francisco, CA – Nov 7-8, 2014
Faculty:
James Drew, Worcester Polytechnic
Institute, Verizon (ret.)
WWW. I NF OR MS . OR G 48 | A NA LY T I CS - MAGA Z I NE . OR G
SOCI AL MEDI A
MEASURE 2: THE “WHAT” – What specifc
activities have any visible/tangible beneft?
Understanding the mission of your audience
is another signifcant step toward engaging
them better. Your social media fock comes to
your page with a specifc intent in mind – is that
information, offers, knowledge or just pure en-
tertainment? Facebook Insights offers a way to
gauge this by looking at the reach of each post
and page. The adventurous-at-heart can down-
load the entire Facebook Insights data at a post
or page level and analyze what content works
and what does not.
The metric of interest here would be the
reach of your posts – differentiated by text, im-
age, video, links or other multimedia options.
The way “reach” should be defned in such a
way that it acts as a proxy for how many peo-
ple “viewed” or “engaged” with the content.
Facebook, LinkedIn and Twitter defne reach
intrinsically. For the others, which do not have
an explicit “reach” metric, a proxy of number of
views or number of clicks can be taken.
An eventual insight from this exercise should
help you precisely understand what the cus-
tomer expects from your social media channel
– is it an image with a collage of discount offers
or is it a DIY video of how-to-use-a-product-
smartly or is it plain old philosophy on things?
MEASURE 3: THE “WHY” – Why does specifc
content work better than the others?
A video or an image is not quite actionable
in itself. What is more important is the content
Your social media flock
comes to your page with
a specific intent in mind –
is that information, offers,
knowledge or just pure
entertainment?
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 49
within the image, which makes the multi-
media work.
The metric of interest here would be
a mixture of the sentimental response to
your posts and the contextual messag-
es contained in those posts. Sentiment
analysis is a simple enough exercise
in an open sourced platform like R or
other online sources, which can provide
a rundown of the positive and negative
views for each post. A contextual analy-
sis of each post based on its theme can
help users understand why a specifc
post is more preferred compared to the
others.
An eventual insight from this exer-
cise should help users fgure out why a
Figure 1: Five measures of social media karma.
customer likes a post and how they feel
about it. Many social media listening cen-
ters set up by big corporate houses focus
specifcally on this part – real-time man-
agement of sentiments and assuaging
the angry customer.
MEASURE 4: THE “WHEN” – When
does a time-bound game plan work
according to the plan?
Time is one of the most critical ele-
ments of a social media strategy. You
cannot go around posting any time you
want and any number of times you want.
Any refned social media manager worth
their salt would tell you that social me-
dia is an art more than a science, and a
WWW. I NF OR MS . OR G 50 | A NA LY T I CS - MAGA Z I NE . OR G
SOCI AL MEDI A
bigger aspect of this art is knowing when to talk
and when to stay silent.
The metric of interest here would be a
reach of posts (as discussed in Step 2) split
by time of the day and day of the week for dif-
ferent channels. You should be able to fgure
out what time of day or day of week your post
has maximum reach within your audience.
One more thing of interest would be to analyze
the activity period of your followers (possible in
Facebook Insights and Twitter Analytics) and
identify overlapping areas or gaps of improve-
ment between you and your audience’s oper-
ating time.
An eventual insight from this exercise
should arm you better in terms of when to go
onto your channels and update the posts. Many
social media channels now offer the option to
“preset” a post for a specifc day and time in
advance, which can be wisely programmed as
a result of this analysis.
MEASURE 5: THE “HOW” – How is your
audience responding to your efforts?
Looking at CTR (click through rate) or jump-
ing-with-joy (virtually) over follower count is not
the only way to measure social media success.
The only true way of measuring the eventual
success of any social media campaign is if it
translates into real-world currency, one way
or another. Although it’d be a utopian exercise
to tie every single social media activity to the
green buck, there still exist alternate measures
of monetary success.
The only true way of
measuring the eventual
success of any social media
campaign is if it translates
into real-world currency, one
way or another.
Solve key business problems utilizing big data. Earn an
AACSB-International accredited Master of Business
Administration with a specialization in Business Analytics
from the University of South Dakota.
Learn more: www.usd.edu/cde
The University of South Dakota’s
Beacom School of Business has been
continuously accredited by
AACSB-International since 1949.
Advance your career with an online Master of
Business Administration with a specialization
in Business Analytics.
DIVISION OF CONTINUING & DISTANCE EDUCATION
414 East Clark Street | Vermillion, SD 57069
605-677-6240 | 800-233-7937
www.usd.edu/cde | [email protected]
C
M
Y
CM
MY
CY
CMY
K
USD_Online MBA BA Analytics Magazine Ad.pdf 1 6/9/14 9:15 AM
WWW. I NF OR MS . OR G 52 | A NA LY T I CS - MAGA Z I NE . OR G
SOCI AL MEDI A
The metric of interest here would be the sim-
ple overlap (correlation) between the sales at a
point in time and the number of posts “around”
the same point of time. It need not be strictly sales
alone. It could be any metric that captures the es-
sence of all the four points above; it could be new
customers, overall customers, new mentions or
increased engagement. An overlap of a specifc
success metric on a time-on-time basis with a
post’s timings should help you fgure out if your
social media karma is benefcial or otherwise.
An eventual insight from this exercise can
help you better decide on the promotional bud-
get for each type of post and the length of the
promotion. One thing to remember, just like hu-
man karma, the efforts should not be estimated
on an absolute immediate-time basis but with a
practical lag (0-2 days) from the time of posting.
In this interconnected world, where a small
social media ripple can have the impact of a tsu-
nami on the eventual sales bottom line, it be-
comes imperative for analysts to know quick-fx
analyses and easy-to-extract metrics from the
vast unstructured world of social media. It would
be wiser for organizations to analyze data with-
in the security of their own frewalls and derive
some of the key metrics that are more useful for
their purposes – at no extra cost at all. ❙
Kshira Saagar, a manager with Mu Sigma (www.mu-sigma.
com), has considerable experience in analytics consulting
with multiple Fortune 500 clients. His experience spans
across technology, pharmaceutical and retail industries
where he works closely with client teams and business
executives in creating, operationalizing and driving
consumption of analytics.
In this interconnected world,
where a small social media
ripple can have the impact
of a tsunami on the eventual
sales bottom line, it becomes
imperative for analysts to
know quick-fix analyses and
easy-to-extract metrics.
Published for business forecasters, planners, and managers by the International Institute
of Forecasters (IIF), Foresight: Te International Journal of Applied Forecasting delivers
authoritative guidance on forecasting processes, practices, methods, and tools.
Each issue features a unique blend of insights from experienced practitioners and top
academics, distilled into concise and accessible articles, tutorials, and case studies. Our
mission is to help you improve the accuracy and efciency of your forecasting and
operational planning.
Foresight’s topics include
• S&OP process design and management
• Forecasting principles and methods
• Measuring and tracking forecast accuracy
• Regular columns on forecasting intelligence, prediction markets, fnancial forecasting
• Hot new research and its practical value
• Reviews of new and popular books, sofware, and other technologies
No matter what
kind of forecasting
you do, we invite you to
take Foresight for a “test drive.”
To take Foresight for a spin, download a recent issue here:
bit.ly/ForesightTestDrive
Foresight is a publication of the International Institute of Forecasters.
IIF Business Offce: 53 Tesla Avenue, Medford, MA 02155, USA. Tel: 1-781-234-4077
To receive quarterly hard copy issues, unlimited access to our
library of back issues, and much more, subscribe to Foresight here:
forecasters.org/foresight/subscribe
WWW. I NF OR MS . OR G 54 | A NA LY T I CS - MAGA Z I NE . OR G
I NNOVATI VE STATE
The first U.S. chief technology officer claims analytics
holds great promise for promoting public-private
information technology partnerships
an government be both
smaller and better? Can
analytics show the way?
Aneesh Chopra, the frst
chief technology offcer of the United States,
thinks so.
In a new book (“Innovative State: How
New Technologies Can Transform Gov-
ernment”) [1], he argues that public-private
partnership initiatives, utilizing new infor-
mation technology, have already had large
impacts in agencies ranging from the Vet-
erans Administration to Health and Human
Services and from Education to Energy.
He cites numerous examples of success-
es, not confned to his own time in offce,
advancing these initiatives, although the
period 2009-2012, when he was in offce,
he knows best and discusses in the most
detail. He recounts the effort to improve
appointment scheduling for veterans’
health and many federal-state cooperative
BY DOUG SAMUELSON
C
Can government
drive information
innovation?
A NA L Y T I C S
2. The Peter Principle:
People keep advancing
until they attain positions
they cannot fll competent-
ly and then stick there, nei-
ther improving nor getting
removed.
3. Oligarchism: Bu-
reaucracies tend to make
self-preservation the over-
riding priority, engender-
ing stiff resistance to any
attempts to streamline.
4. Olsonism: As renowned
economist Mancur Olson ob-
served, decision-making is often
inordinately infuenced by fero-
ciously determined interest groups
insisting on certain relatively small
policies and resource allocations of great
beneft to them.
5. Information Infarction: Bureau-
cratic decision-making fails because no
one in the bureaucracy can know all the
relevant information. In a top-down, hier-
archical structure, there is little incentive
for people on the front line to present in-
formation that threatens the status quo.
When these people do learn new, relevant
information and pass it upward, the time it
takes for the information to travel up the
chain, be considered and generate direc-
tions is often too long to generate mean-
ingful, timely benefts.
efforts to update school
curricula and involve par-
ents in the process. And, of
course, he claims consid-
erable success for various
aspects of the new health
care system.
These ideas did not
originate with Chopra or
with the Obama administra-
tion. Chopra traces many of
the initiatives to the work of
a group that began meeting in the
late 1980s, as a small number of
well-placed individuals from across
the political spectrum began meet-
ing informally to formulate ways to
make government both more ef-
fcient and more effective. James
Pinkerton, a member of the group, wrote
a book, “What Comes Next” [1995], that
summarized the group’s approach. Pinker-
ton identifed fve general impediments to
implementing innovation:
1. Parkinson’s Law: Work tends to
expand to fll the time and resources avail-
able, as organizations keep fnding justi-
fcations for more resources even when
their area of responsibility is shrinking.
Hence workforces grow even when the or-
ganizations’ responsibilities do not. (Par-
kinson also noted that one reason for this
is that people in a hierarchy seek to multi-
ply subordinates, not potential rivals.)
S E P T E MB E R / OCT OB E R 2014 | 55
Aneesh
Chopra
WWW. I NF OR MS . OR G 56 | A NA LY T I CS - MAGA Z I NE . OR G
I NNOVATI VE STATE
While acknowledging the importance
of these aspects of bureaucracy, Chopra
nevertheless insists that the information
technology revolution that began in the late
1990s has created the conditions for a new
structure to break through the impediments.
He built on his own background, frst his
education at The Johns Hopkins University
and the Kennedy School of Government
(Harvard), then as an entrepreneur and
later as chief technology offcer of the Com-
monwealth of Virginia in the Tim Kaine ad-
ministration (2006-2010) to make the case
(with a strong endorsement from Governor
Kaine) to newly elected President Obama
for how a national chief technology offcer
could help the country.
He cites the “open innovation” con-
cepts of Henry Chesbrough, professor of
business administration at the University
of California, Berkeley, as the moving force
behind much of the high-tech innovation
of private businesses in the 1990s. Ches-
brough emphasized “giving more informa-
tion to more people sooner” as the key
idea. Applied to government, this means
using government “to liberate or harness
the energies of the private sector.” This ap-
proach involves four tool sets:
1. Open data: enabling the public to ac-
cess more government digital data, not
only for transparency but also, more im-
portant, so that the information can be in-
corporated in new products or services.
2. Impatient convening: Government’s
inviting the private sector to work collab-
oratively on standards that lower barriers
to entry and foster competition.
3. Challenges and prizes: Widely inviting
proposals to solve a particular problem,
outside the cumbersome and often waste-
ful government procurement processes.
4. Attracting talent: Recruiting entrepre-
neurs into the government to manage the
preceding three tool sets to focus on actu-
al accomplishments and stimulate break-
through results in a tight time frame.
In his book, Chopra cites a number of
examples of apparent successful and con-
sequential implementation, including De-
partment of Health and Human Services
initiatives to make health data more widely
available and useful; a San Francisco Bay
Area project to make zoning information
and requirements more readily available
to prospective commercial tenants; a pub-
licly available website to track and display
legislative proposals in Virginia online; and
the movement of the Federal Register, the
offcial record of activities and proposed
actions throughout the federal govern-
ment, to a readily accessible and indexed
public website.
In recent comments about what he
learned on his book tour, he says, “On
my journey thus far, including stops on
the ‘Daily Show’ and ‘Morning Joe,’ I’ve
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 57
confronted a more pessimistic view that
the hyper-partisanship in Washington
is standing in the way of any meaning-
ful progress. Perhaps my most memo-
rable exchange took place at an event
organized by my dear friend and conve-
ner-in-chief, Coach Kathy Kemper, on
the growing interest in the ‘Internet of
Things.’
“Supreme Court Justice Stephen Brey-
er expressed some skepticism as to our
nation’s ability to fully harness the power
of information technology, citing a paper
he co-authored in the 1970s on ‘time of
use’ pricing models that were expected to
dramatically accelerate energy effciency,
but fell short, in part on the failure of our
governance system. He mused of a new
‘call to action’ on elevating civics educa-
tion. He asked why we couldn’t harness
these technologies to cull together a 21st
century civics curriculum to include a mini-
lecture by President Obama on the origi-
nal Magna Carta, opening up the treasure
trove of artifacts held at the U.S. Consti-
tution Center and across our network of
libraries, among other ideas.”
Chopra continues: “I responded with
three points: First, that part of the problem
on realizing the value of time-of-use pric-
ing was an information gap between data
held by the utilities on energy utilization
(and the regulators on the specifc rate
plans) and the creativity of entrepreneurs
competing on how to best present that
data for action by consumers. I shared an
example from the book on Green Button
(www.greenbuttondata.org), a voluntarily-
designed data standard adopted at frst by
three of California’s largest utilities to open
up machine-readable access to energy
usage data by consumers (and through
Green Button Connect, their trusted third
parties). Within a week of Green Button’s
launch, an entrepreneur in New York City
built ‘Watt Quiz,’ a game that pulled in rate
and usage data to inform consumers on
the best rate plan that would save them
money without impacting their current uti-
lization patterns (true low hanging fruit).
“Second,” he went on, “I spoke of
the governance model that has enabled
this voluntary standard to scale. Rather
than a single institution declaring such a
policy be implemented – with the associ-
ated costs of likely a bloated IT acquisi-
tion – we pursued a version of former
President Herbert Hoover’s vision of an
‘Associative State’ that emphasized gov-
ernment’s role as ‘convener’ rather than
regulator, or direct investor. One phone
call from me to PG&E’s CIO, Karen
Austin, kicked off a series of voluntary
collaborations that have since resulted
in commitments by utilities serving 60
million households (over 100 million
people) to adopt the Green Button data
standard.
WWW. I NF OR MS . OR G 58 | A NA LY T I CS - MAGA Z I NE . OR G
I NNOVATI VE STATE
“Third,” he concluded, “I highlighted our work
with Education Secretary Arne Duncan on the
‘Open Education Data Initiative’ to fip the model
of top-down curriculum development (whether
for civics or other topics) to a more democratiz-
ing model harnessing a new ‘Learning Registry’
standard that empowers teachers and stakehold-
ers to ‘tag’ any learning object on the Internet,
including the ability to share peer ratings and
reviews. Anyone can now contribute pieces and
parts for a new civics course that can be more
rapidly assembled for use by schools, non-proft
institutions or parents. All at no charge. Rather
than await some centrally designed civics curric-
ulum for all to adopt, we’ve lowered barriers for
everyone to deliver world-class civics instruction
at a pace that is right for them. How did Justice
Breyer respond? He said he would be buying my
book.”
Although Chopra’s enthusiasm is infectious
and his examples are persuasive, serious is-
sues remain. Long-time readers of OR/MS To-
day may remember reports of a broad, strongly
backed initiative toward a standard electronic
patient record in health care and other IT efforts
20 years ago [Samuelson, 1995]. Many knowl-
edgeable people asserted, as we reported, that
information problems were most likely the sin-
gle biggest driver of both high costs and quality
problems. Five years later, the National Institute
of Medicine announced much the same con-
clusion. Still, very recent studies indicate that
many of the same problems persist [James and
Samuelson, 2013].
Rather than await some
centrally designed civics
curriculum for all to adopt,
we’ve lowered barriers
for everyone to deliver
world-class civics instruction
at a pace that is right
for them.
▪ 30-credit-hour curriculum
with admission in Fall and
Spring semesters
▪ Gain skills in demand by
industrial, research, and
commercial firms
▪ Concentrations available:
Logistics and Supply Chains,
Energy Systems, and Lean
Six Sigma
Now Accepting Applications
DistanceEd.uncc.edu
704-687-1277
Master of Science in
ENGINEERING
MANAGEMENT
Delivered Online
A Technical Alternative to the MBA
Fast track option available – Finish in 12 months!
WWW. I NF OR MS . OR G 6 0 | A NA LY T I CS - MAGA Z I NE . OR G
I NNOVATI VE STATE
SAS and Hadoop take on
the Big Data challenge.
And win.
Analytics
Why collect massive amounts of Big Data if you can’t analyze
it all? Or if you have to wait days and weeks to get results?
Combining the analytical power of SAS with the crunching
capabilities of Hadoop takes you from data to decisions in a
single, interactive environment – for the fastest results at the
greatest value.
Read the TDWI report
sas.com/tdwi
SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. ® indicates USA registration. Other brand and product names are trademarks of their respective companies. © 2014 SAS Institute Inc. All rights reserved. S120598US.0214
Similarly, alert readers will note the
irony of the disappointing developments,
since the book appeared, in one of Cho-
pra’s best examples, the VA scheduling
system. Many of the improvements he
claims really did take place – but not en-
tirely system-wide. The rollout of the new
healthcare system also provides both
positive and negative evidence about his
proposed approaches. (Much of the dif-
fculty can be traced, he points out, to a
single major procurement done “the old
way,” resulting in a bad technical solution
to one key component.) Substantial analy-
sis remains to be done about how to get
the more entrenched, change-resistant
components of a large organization to go
along with major innovation, or to come up
with different improvements of their own.
Chopra admits that he generated many
more good ideas than he saw through to
completion, leading his wife to call him “the
Secretary of Memos.” One is led to suspect
that individual leadership and persuasive-
ness play a larger role, and systems con-
cepts a correspondingly lesser role, than
Chopra and analytics professionals would
like to admit. This implies that leadership
style is one of the important subjects of study.
Even more important, how to evaluate what
proposed changes are working and how to
focus on the real causes of problems is an
ongoing challenge that analytics profession-
als are especially well qualifed to address.
Chopra also points out that the current
news media culture and climate tends to
focus on contentious issues and embar-
rassing shortcomings, while under-report-
ing large-scale but relatively slow-moving
system changes. Here, too, analytics pro-
fessionals could be helpful, by digesting
meaningful information and presenting it to
news outlets in ways they can readily uti-
lize. Chopra’s book and public appearanc-
es are an attempt to do this, along with his
active participation in electoral politics. (He
ran, unsuccessfully, for lieutenant governor
of Virginia last year and is currently very ac-
tive in Senator Mark Warner’s re-election
campaign.) In short, he doesn’t have all the
answers – but he is defnitely raising many
of the right questions, and analytics profes-
sionals would do well to respond.
Doug Samuelson ([email protected])
is president and chief scientist of InfoLogix, Inc., in
Annandale, Va., and a senior operations research
analyst with Group W, Inc., in Merrifeld and
Triangle, Va., supporting the Marine Corps Combat
Development Command (MCCDC). He is a longtime
member of INFORMS and a contributing editor of
OR/MS Today and Analytics.
NOTES & REFERENCES
1. Aneesh Chopra, “Innovative State: How New
Technologies Can Transform Government,” New York,
Atlantic Monthly Press, 2014.
2. Brent James and Douglas A. Samuelson, “Change
We Can Live With: Building the Data Capabilities and
Analytics to Make Critical Improvements in Patient
Safety and Wellness,” OR/MS Today, October 2013.
3. James Pinkerton, “What Comes Next: The End of
Big Government – and the New Paradigm Ahead,”
New York: Hyperion, 1995.
4. Douglas A. Samuelson, “Diagnosing the Real
Health Care Villain,” OR/MS Today, February 1995.
J U LY / AU GU S T 2014 | 61 A NA L Y T I C S
SAS and Hadoop take on
the Big Data challenge.
And win.
Analytics
Why collect massive amounts of Big Data if you can’t analyze
it all? Or if you have to wait days and weeks to get results?
Combining the analytical power of SAS with the crunching
capabilities of Hadoop takes you from data to decisions in a
single, interactive environment – for the fastest results at the
greatest value.
Read the TDWI report
sas.com/tdwi
SAS and all other SAS Institute Inc. product or service names are registered trademarks or trademarks of SAS Institute Inc. in the USA and other countries. ® indicates USA registration. Other brand and product names are trademarks of their respective companies. © 2014 SAS Institute Inc. All rights reserved. S120598US.0214
WWW. I NF OR MS . OR G 62 | A NA LY T I CS - MAGA Z I NE . OR G
BY CANDACE
“CANDI” YANO
CONFERENCE PREVI EW
The 2014 INFORMS Annual Meeting in San
Francisco, set for Nov. 9-12 and whose theme is
“Bridging Data and Decisions,” promises to be one
of the largest ever, with more than 5,000 technical
presentations. Whether you are interested in press-
ing societal needs, including healthcare, energy and
climate change, new developments in supply chain
management and logistics, cutting-edge method-
ologies for optimization, or advances in stochastic
processes and risk analysis, you will fnd hundreds
of presentations to match your interests. Special
practice-oriented tracks will offer a view into how
companies, large and small, have successfully im-
plemented various analytics approaches to improve
the bottom line.
Also featured are diverse plenary and keynote
talks spanning a lecture by Nobel laureate Alvin
Roth to a presentation on the Google Driverless Car
San Francisco conference
to bridge data, decisions
Special practice-oriented
tracks will offer a view
into how companies,
large and small, have
successfully implemented
various analytics
approaches to improve the
bottom line.
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 63
Project. Other highlights include special
lectures and sessions to commemorate
what would have been the 100th birth-
day of the late George Dantzig.
The conference will take place in two
adjacent hotels, the Hilton San Fran-
cisco Union Square and the Parc 55
Wyndham, in close proximity to the city’s
prime shopping district and near major
tourist sites, major cultural attractions
and world-class restaurants.
Nearly 50 years ago, Scott McKenzie
sang, “If you’re going to San Francisco,
be sure to wear some fowers in your
hair.” The conference will offer still
another suggestion: Be sure to come to
the 2014 INFORMS Annual Meeting. It
will be an exceptional venue for recon-
necting with professional colleagues and
making new ones. ❙
For more information, click here.
Candi Yano is a professor in the Department of
Industrial Engineering and Operations Research
and in the Haas School of Business at the
University of California-Berkeley and general chair
of the INFORMS Annual Meeting in San Francisco.
The INFORMS Career Center offers
employers expanded opportunities to
connect to qualified O.R. and analytics
professionals. For many years INFORMS
Job Placement Service has helped both job
seekers and recruiters make the right
connections. INFORMS new center now
offers a complete line of services to be used
alone or in conjunction with the Job Fair at
the 2014 Annual Meeting. Both give
applicants and employers a convenient
venue to connect. The Career Center is free
to INFORMS member applicants.
SEARCHING?
HIRING?
For info on job fair at the 2014 INFORMS Annual Meeting,
http://meetings.informs.org/sanfrancisco2014/jobfair.html
Refreshed &
Reinvigorated
INFORMS
CAREER CENTER
• More analytics jobs
• Preferred jobs
• Featured jobs
• Job alerts
• Anonymous career profiles
• Powerful searching capabilities
CAREER
CENTER
WWW. I NF OR MS . OR G 64 | A NA LY T I CS - MAGA Z I NE . OR G
The Winter Simulation Conference (WSC) has
been the premier international forum for disseminat-
ing recent advances in the feld of system simula-
tion for more than 40 years, with the principal focus
being discrete-event simulation and combined dis-
crete-continuous simulation. In addition to a techni-
cal program of unsurpassed scope and high quality,
WSC provides the central meeting place for simu-
lation researchers, practitioners and vendors work-
ing in all disciplines and in industrial, governmental,
military, service and academic sectors. WSC 2014
will be held Dec. 7-10 in Savannah, Ga., at the Wes-
tin Savannah Harbor Golf Resort & Spa and the ad-
jacent Savannah International Trade & Convention
Center.
The appeal of simulation is its relevance to a di-
verse range of interests. WSC has always refected
this diversity, and WSC 2014 aligns with and ex-
pands upon this tradition. For those more inclined
to the academic aspects of simulation, the confer-
ence offers tracks in modeling methodology, analy-
sis methodology, simulation-based optimization,
hybrid simulation and agent-based simulation. For
those more inclined to the application of simulation,
tracks include healthcare, manufacturing, logistics
WSC 2014: Exploring big
data through simulation
BY STEPHEN J. BUCKLEY
WSC has been the
premier international
forum for disseminating
recent advances in the
field of system simulation
for more than 40 years.
WSC 2014
to join online visit
http://join.informs.org
▪ Certification for Analytics Professionals
▪ A FREE Community Membership
▪ Continuing Ed courses for Analytics Professionals
▪ Online access to the latest in operations research
and advanced analytics techniques
▪ Unsurpassed Networking Opportunities available
in INFORMS Communities and at Meetings
▪ Subscriptions to online and print INFORMS Publications
▪ INFORMS Career Center - the industry’s leading job board
JOIN
Is the largest association for analytics in the
center of your professional network?
It should be.
WWW. I NF OR MS . OR G 66 | A NA LY T I CS - MAGA Z I NE . OR G
WSC 2014
and supply chain management, military
applications, business process model-
ing, project management and construc-
tion, homeland security and emergency
response, environmental and sustain-
ability applications, and networks and
communications.
The Modeling and Analysis of Semi-
conductor Manufacturing (MASM) is a
conference-within-a-conference featur-
ing a series of sessions focused on the
semiconductor feld. The Industrial Case
Studies track affords industrial practitio-
ners the opportunity to present their best
practices to the simulation community.
The Simulation Education track presents
approaches to teaching simulation at ed-
ucation levels ranging from K-12 to grad-
uate and professional workforce levels.
Finally, WSC provides a comprehensive
suite of introductory and advanced tutori-
als presented by prominent individuals in
the feld, along with a lively poster ses-
sion, Ph.D. colloquium, a new attendee
orientation and a distinguished speaker
lunchtime program.
The theme for WSC 2014, “Explor-
ing Big Data Through Simulation,” is
timely and relevant. The explosion of
data throughout the world has created
both opportunities and challenges to
business and technical communities. In
this conference, presenters will discuss
how simulation can help. In addition to
special tracks on big data simulation
and decision-making and scientifc ap-
plications, conference keynote speaker
Robert Roser, head of scientifc com-
puting at Fermi National Accelerator
Laboratory in Batavia, Ill., and one of
the world’s leading experts on experi-
mental particle physics, will speak about
the recently discovered Higgs Boson
particle and the role of simulation in the
discovery. The military keynote speaker
is Greg Tackett, director of the Ballistic
Missile Defense Evaluation Directorate
(BMDED) and the Ballistic Missile De-
fense System Operational Test Agency
(BMDS OTA), U.S. Army Test and Eval-
uation Command, Redstone Arsenal,
Alabama.
The WSC is designed for profes-
sionals at all levels of experience across
broad ranges of interest. The extensive
cadre of exhibitors and vendor presenta-
tions, the meetings of various profession-
al societies and user groups, along with
the various social gatherings, give all at-
tendees the opportunity to get acquainted
with each other and to become involved
in the ever-expanding activities of the in-
ternational simulation community. ❙
For more, click here.
Stephen J. Buckley is a research staff member
at the IBM Thomas J. Watson Research Center
in Yorktown Heights, N.Y., and general chair of
WSC 2014.
USINESS ANALYTICS &
PERATIONS RESEARCH
INFORMS CONFERENCE ON
Huntington Beach
APRIL 12-14, 2015
Catch the Wave:
Real-World Analytics Solutions
Missed this years conference?
Review meeting highlights from 2014.
meetings.informs.org/analytics2014
Present a Talk or
Poster and Save
Present your work at the conference
known for real-world analytics and
save on registration. Case studies,
best practice examples, and academic
research with a practitioner orienta-
tion are all welcome.
Submission Deadlines
Oral Presentations
December 19, 2014
Poster Presentations
January 16, 2015
Learn how Analytics and O.R.
can maximize the value of your data
to drive better business decisions.
Real-world use of descriptive, predictive,
and prescriptive analytics
Focus on big data, marketing analytics,
healthcare applications
Most rigorous and real world analytics
conference offered
Administration of Certified Analytics
Professional (CAP
®
) exam
Not just what to do but HOW TO DO IT
Only INFORMS can provide an analytics and O.R.
conference backed up by the best minds in industry
and academia. Hand-picked speakers take you through
case studies on how analytics can maximize the value
of your data, driving better business decisions, and
impacting the bottom line.
WWW. I NF OR MS . OR G 68 | A NA LY T I CS - MAGA Z I NE . OR G
FI VE-MI NUTE ANALYST
Lately I’ve been interested in textual data, which
has opened a whole new world of things to think – and
write – about. One interesting thing about text data
is that the entire world of written word becomes your
analytic garden. While exploring this garden, I thought
it would be interesting to take a look at the presidents’
State of the Union addresses through the years.
The State of the Union is an annual report from
the president of the United States to Congress. It can
be a venue for rolling out new policies and strategies.
We can safely assume that each administration takes
the preparation and delivery of this speech very seri-
ously, and puts the best resources they have into it.
Therefore, the addresses may be considered a “snap-
shot” of the writing style of their time. The speeches
can be found for all the presidents at a number of
places; I used the American Presidency Project [1].
For this analysis, we consider the frst term speeches
by the following presidents: Madison, Lincoln, Ken-
nedy, Clinton, Bush (George W.) and Obama.
Calculating “readability” via machine methods
seems diffcult at frst. Fortunately, there are a num-
ber of methods available. The one that I decided to
use is the “Flesch-Kincaid Grade Level” [2], given by:
This test has several desirable properties; it is
straightforward to calculate because word and syl-
lable counts are easily counted by machine. Second,
State of the Union
BY HARRISON
SCHRAMM, CAP
One interesting thing
about text data is that
the entire world of written
word becomes your
analytic garden. While
exploring this garden,
I thought it would be
interesting to take a look
at the presidents’ State
of the Union addresses
through the years.
A NA L Y T I C S S E P T E MB E R / OCT OB E R 2014 | 69
it is invariant to the meaning of the spe-
cifc passages, so it can be used equally
against samples written in different styles
or time periods. The second desirable
property is also its main drawback. Spe-
cifcally, the term “grade level” can be
misleading, because it applies only to
structure and not meaning. For example:
“It is a far, far better thing that I do than
I have ever done; it is a far, far better rest
that I go to than I have ever known” [3],
and “I went to the grocery store, bought
some rye bread and ate it all up” [4].
The statements are clearly written at
different intellectual levels, but both score
3.6 on the Flesch-Kincaid scale.
Many packages are available to do this
type of analysis; the analysis that follows
was done using the “koRpus” [5] package
for R. Our exploration of some presidents’
addresses are presented in Figure 1.
For sake of comparison, Lincoln’s
Gettysburg Address [6] has a grade level
of 11.5, The Enchiridion by Epictetus [7]
Figure 1: Flesch-Kincaid (FK) grade level of State of the Union a0ddresses for selected presidents.
The data suggests a decline in complexity from Madison and Lincoln to present. The most recent
three presidents (Clinton, G.W. Bush and Obama) are statistically indistinguishable as measured by FK
(ANOVA p = .66). This is a refection of the writing style of the time, more than the education level of
the various presidents (and their staffs). Lincoln and Kennedy are similar (p = .25), while Madison was
writing in a different grade level (p = .001).
WWW. I NF OR MS . OR G 70 | A NA LY T I CS - MAGA Z I NE . OR G
FI VE-MI NUTE ANALYST
has a grade level of 7.8, and my June
Five-Minute Analyst column [8] has a
grade level of 8.6. Conversely, “The Cat
in the Hat” by Dr. Seuss, consisting of
short sentences and monosyllabic words,
scores -.36.
DOES THIS MATTER?
The writing style of the presidents is
not only a refection of themselves, but
also of the times that they live and the
audience to which they are speaking. It
should not surprise us that in the mod-
ern era, presidents speaking to the entire
electorate in real time via TV and radio
have a lower grade level than Madison,
who was speaking to a smaller audience.
Those who wish for a more “intellectual”
discourse with our leaders should con-
sider the opening paragraph of Madison’s
1809 address:
“At the period of our last meeting I had
the satisfaction of communicating an ad-
justment with one of the principal belliger-
ent nations, highly important in itself, and
still more so as presaging a more extend-
ed accommodation. It is with deep concern
I am now to inform you that the favorable
prospect has been over-clouded by a re-
fusal of the British government to abide by
the act of its minister plenipotentiary, and
by its ensuing policy toward the United
States as seen through the communica-
tions of the minister sent to replace him.”
It will be interesting in future years to
see if the apparent diffculty of texts stabi-
lizes, increases or decreases. At this mo-
ment, I would believe all three outcomes.
Harrison Schramm (harrison.schramm@gmail.
com) is an operations research professional in the
Washington, D.C., area. He is a member of INFORMS
and a Certifed Analytics Professional (CAP).
Request a no-obligation INFORMS Member Benefits Packet
For more information, visit: http://www.informs.org/Membership
NOTES & REFERENCES
1. http://www.presidency.ucsb.edu/sou.php#menu
2. Kincaid, J. P., 1975, “Derivation of New Readability
Formulas for Navy Enlisted Personnel,” Research
Branch Report 8-75, Millington, Tenn.
3. The closing of “A Tale of Two Cities” by Charles
Dickens.
4. A sentence I just made up for this purpose.
5. http://cran.r-project.org/web/packages/koRpus/
index.html
6. http://www.abrahamlincolnonline.org/lincoln/
speeches/gettysburg.htm
7. As translated by George Long: http://www.ptypes.
com/enchiridion.html
8. http://www.analytics-magazine.org/july-august-
2014/1080-fve-minute-analyst-probabilistic-parking-
problems
About the Competition
The purpose of the competition is to bring forward, recognize, and reward
outstanding examples of operations research and the management sciences
in practice. The client organization that uses the winning work receives a
prize citation; the authors of the winning work receive a cash award.
Entry Requirements
Visit the website www.informs.org/edelmanaward for detailed information.
Entries should report on a completed practical application and must describe
results that had a signifcant, verifable, and preferably quantifable impact
on the performance of the client organization. Finalist work will be published
in the January-February 2016 issue of Interfaces.
Any work you have done in recent years is eligible, unless it has previously
been described by a Franz Edelman Award fnalist. Previous publication of
the work does not disqualify it. Anyone is eligible for the competition except
a member of the judging panel.
E-mail Submissions
Please e-mail your submission to:
[email protected]
Michael Trick
Chair, 2015 Edelman Award Competition Commitee
Call for Entries
Application Deadline: October 15, 2014
A $15,000 Competition with a $10,000 First Prize
Key Dates for the Competition
Wednesday, October 15, 2014
Deadline to provide a single pdf document
containing a three page summary of your
achievement, and a cover page with a
60-word abstract, and the name, address,
phone number, and afliation of each author.
Monday, December 16, 2014
Finalists will be selected based on the
summaries and the INFORMS/CPMS
verifcation process.
Friday, February 14, 2015
Deadline for fnalists to provide a full
writen paper.
Monday, April 13, 2015
Each fnalist group will give an oral
presentation of their work in a special session
at the INFORMS Conference on O.R. Practice
in Huntington Beach, CA, April 12-14, 2015.
The PracƟce SecƟon of INFORMS
CPMS CPMS
The PracƟce SecƟon of INFORMS
Daniel H. Wagner Prize: Excellence in O.R. Practice
INFORMS Prize: Effective Integration in Organizations
Industry Job Search Panel Discussion
GREAT ANALYTICS
PRACTICE “MEETING
WITHIN A MEETING”
AT 2014 INFORMS
ANNUAL MEETING
Meet the people that care about what
you care about.
Monday, November 10, 6:15 – 7:15 pm
Industry sessions span entire
meeting November 9–12, 2014
Attend the Analytics Section
Meet and Greet
Register Here: meetings.informs.org/sanfrancisco2014/register.html
Analytics Magazine readers are invited to
meet one-on-one or in small groups with
INFORMS Analytics Section officers in San
Francisco. We’ll help you arrange. For details,
email [email protected].
Receive Individual Consulting
Recology is one of the nation’s 10 largest 100%
employee-owned businesses, and has been recycling
refuse for over 90 years. It piloted the first curbside
compost collection program in the U.S., and launched
the first program in the U.S. to create electricity using
anaerobic digestion of source-separated food scraps.
Recology Plant Tour
Think the INFORMS Annual Meeting is only for Academics? Think again.
WWW. I NF OR MS . OR G 72 | A NA LY T I CS - MAGA Z I NE . OR G
THI NKI NG ANALYTI CALLY
As the owner of a fast food restaurant with declin-
ing sales, your customers are looking for something
new and exciting on the menu. Your market research
indicates that they want a burger that is loaded with
everything as long as it meets certain health require-
ments. Money is no object to them.
The ingredient list in Table 1 shows what is avail-
able to include on the burger. You must include at least
one of each item and no more than fve of each item.
You must use whole items (for example, no half serv-
ings of cheese). The fnal burger must contain less
than 3,000 mg of sodium, less than 150 grams of fat
and less than 3,000 calories.
To maintain certain taste quality standards you’ll
need to keep the servings of ketchup and lettuce the
same. Also, you’ll need to keep the servings of pickles
and tomatoes the same.
QUESTION: What is the most expensive burger
you can make?
Send your answer to [email protected] by
Nov. 15. The winner, chosen randomly from correct
answers, will receive a $25 Amazon Gift Card. Past
questions can be found at puzzlor.com.
BY JOHN TOCZEK
John Toczek is the senior director
of Decision Support and Analytics for
ARAMARK Corporation in the Global
Operational Excellence group. He
earned a bachelor of science degree
in chemical engineering at Drexel
University (1996) and a master’s
degree in operations research from
Virginia Commonwealth University
(2005). He is a member of INFORMS.
The PuzzlOR & Thinking Analytically
B Y J O H N T O C Z E K
Good Burger
Item
Sodium
(mg) Fat (g) Calories
Item cost
($)
Beef Patty 50 17 220 $0.25
Bun 330 9 260 $0.15
Cheese 310 6 70 $0.10
Onions 1 2 10 $0.09
Pickles 260 0 5 $0.03
Lettuce 3 0 4 $0.04
Ketchup 160 0 20 $0.02
Tomato 3 0 9 $0.04
As the owner of a fast food restaurant with declining sales, your customers are looking for something
new and exciting on the menu. Your market research indicates that they want a burger that is loaded
with everything as long as it meets certain health requirements. Money is no object to them.
The ingredient list in the table shows what is available to include on the burger. You must include at
least one of each item and no more than five of each item. You must use whole items (for example, no
half servings of cheese). The final burger must contain less than 3000 mg of sodium, less than 150
grams of fat, and less than 3000 calories.
To maintain certain taste quality standards you’ll need to keep the servings of ketchup and lettuce the
same. Also, you’ll need to keep the servings of pickles and tomatoes the same.
Question: What is the most expensive burger you can make?
Send your answer to [email protected] by October 15
th
, 2014. The winner, chosen randomly from
correct answers, will receive a $25 Amazon Gift Card. Past questions can be found at puzzlor.com.
John Toczek is the Sr. Director of Decision Support and Analytics for Aramark Corporation in the Global Operational Excellence
group. He earned his BSc. in Chemical Engineering at Drexel University (1996) and his MSc. in Operations Research from
Virginia Commonwealth University (2005).
pXX OR/MS TODAY and Analytics Magazine August 2014 v1
The PuzzlOR Thinking Analytically
Good
burger
The PuzzlOR & Thinking Analytically
B Y J O H N T O C Z E K
Good Burger
Item
Sodium
(mg) Fat (g) Calories
Item cost
($)
Beef Patty 50 17 220 $0.25
Bun 330 9 260 $0.15
Cheese 310 6 70 $0.10
Onions 1 2 10 $0.09
Pickles 260 0 5 $0.03
Lettuce 3 0 4 $0.04
Ketchup 160 0 20 $0.02
Tomato 3 0 9 $0.04
As the owner of a fast food restaurant with declining sales, your customers are looking for something
new and exciting on the menu. Your market research indicates that they want a burger that is loaded
with everything as long as it meets certain health requirements. Money is no object to them.
The ingredient list in the table shows what is available to include on the burger. You must include at
least one of each item and no more than five of each item. You must use whole items (for example, no
half servings of cheese). The final burger must contain less than 3000 mg of sodium, less than 150
grams of fat, and less than 3000 calories.
To maintain certain taste quality standards you’ll need to keep the servings of ketchup and lettuce the
same. Also, you’ll need to keep the servings of pickles and tomatoes the same.
Question: What is the most expensive burger you can make?
Send your answer to [email protected] by October 15
th
, 2014. The winner, chosen randomly from
correct answers, will receive a $25 Amazon Gift Card. Past questions can be found at puzzlor.com.
John Toczek is the Sr. Director of Decision Support and Analytics for Aramark Corporation in the Global Operational Excellence
group. He earned his BSc. in Chemical Engineering at Drexel University (1996) and his MSc. in Operations Research from
Virginia Commonwealth University (2005).
pXX OR/MS TODAY and Analytics Magazine August 2014 v1
The PuzzlOR Thinking Analytically
Table 1: For the best burger, cost is no object.
GENERAL ALGEBRAIC MODELING SYSTEM
[email protected] www.gams.com
• Players take on the role of
farmers working to sustainably
grow crops as energy resources,
earn income and improve
ecosystem services.
• Automated ‘bot’ players
communicate with the optimiza-
tion models via the GAMS Java
API to evaluate which options
will maximize their overall
game score.
• The game can be played in a
variety of settings, but was
primarly designed for use in
high school and undergraduate
classes.
For further information please visit http://www.feldsoffuel.org
or contact Steven Wangen - [email protected]
Fields of Fuel - A Multiplayer, Web-based Simulation Game
A complex system of GAMS models is a centerpiece of this free web-based simulation game,
which allows players to explore sustainability issues associated with bioenergy crop production.
Biofuels and agronomic experts assisted in creating an accurate and realistic depiction of the
system dynamics.
©
L
u
c
k
y
D
r
a
g
o
n
-
F
o
t
o
l
i
a
.
c
o
m
GAMS Integrated Developer Environment for editing,
debugging, solving models, and viewing data.
High-Level Modeling
The General Algebraic Modeling System (GAMS) is a high-level
modeling system for mathematical programming problems.
GAMS is tailored for complex, large-scale modeling applications,
and allows you to build large maintainable models that can be
adapted quickly to new situations. Models are fully portable from
one computer platform to another.
State-of-the-Art Solvers
GAMS incorporates all major commercial and academic state-of-
the-art solution technologies for a broad range of problem types.
