Simplify360 eBook: Predictive Analytics The Future of Social Media pdf

World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media

1
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
Table of Contents
PREFACE 3
WHAT ARE PREDICTIVE ANALYTICS? 5
ADITYA CHOWDHARY - CLIENT SERVICES DIRECTOR MARKETELLIGENT 5
BEYOND SENTIMENTS 10
ZISHAN ANSARI - SENIOR BUSINESS ANALYST, TARGET CORPORATION 10
SOCIAL MEDIA STRATEGIES FOR THE DATA DRIVEN NEWSROOM 17
DENNIS MORTENSEN – CEO, VISUAL REVENUE 17
TOO MUCH TALK IN ANALYTICS & TOO LITTLE ACTION! 24
AJAY KELKAR – COO, HANSA CEQUITY 24
ACTIONABLE ANALYTICS 28
JAMES TAYLOR – CEO, DECISION MANAGEMENT SOLUTIONS 28
UNDERSTANDING AND MEASURING SOCIAL INFLUENCE 34
ARUN SUNDARARAJAN - PROFESSOR AND NEC FACULTY FELLOW, NEW YORK UNIVERSITY’S STERN SCHOOL
OF BUSINESS 34
HOW SOCIAL MEDIA CAN REVEAL THE MYSTERY OF BRAND LOYALTY! 37
G.K SURESH - GENERAL MANAGER, ITC FOODS 37
SCRM IN 2013: NEXT GEN SOCIAL MEDIA ANALYTICS 44
BHUPENDRA KHANAL – CEO, SIMPLIFY360 44
SOCIAL MEDIA BEST PRACTICES 53
ANKITA GABA - CO-FOUNDER, SOCIAL SAMOSA 53

INSIDE BIG DATA – WHAT’S IN IT FOR MARKETING? 57
DEEP SHERCHAN – CMO, SIMPLIFY360 57
SOCIAL MEDIA PREDICTIONS FOR 2013 62
PRASHANT JAIN - SOCIAL MEDIA ANALYST, SIMPLIFY360 62
2
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
Preface
Today enterprises are overwhelmed with the possibility of social media. It’s
been proven that it is no longer a fad and it means serious business. At this
turning event of realization, enterprises are not equipped with right tools
and human resources to leverage social media.
On the other hand, we are seeing a rapid innovation in the field of social
media tools and technologies – social monitoring, analytics, marketing,
intelligence, scrm, big data etc.
As a result, we at Simplify360 tried to connect with different professionals
active in this field of social analytics and learn from them about the future
of social media. In this process we kept hearing predictive analytics as a
repeating term. Hence we asked our team to reach out to the experts in the
field and learn about what does predictive analytics mean in social media
and its role in the future of social media.
We would like to thank all the people who have agreed to share their
experience and knowledge about social media.
3
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media

What Are Predictive Analytics?
Aditya Chowdhary
Aditya Chowdhary, has over 16 years of experience in areas of Application Development, Marketing and Social
Media Analytics. He has worked with global companies like GE, Dell. He was instrumental at Dell to setup the
Social Media Analytics practice and very recently has joined Marketelligent.
4
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
What are predictive analytics?
Aditya Chowdhary - Client Services Director Marketelligent
Predictive analytics have been around for a long time and slowly these
analytic
tools are finding their way into the marketing and social media arenas.
Predictive analytics use behavioural data from past
to predict how individuals will behave in the future.
For instance, your credit score is a predictive model including your
repayment history and other information to predict whether you're a good
credit risk or not.
Predictive models commonly include a number of variables, such as number
of late
payments, and weighing factors that reflect the importance of that variable
in predicting future behavior. These are commonly regression-type models.
5
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
Modern predictive analytics use similar kind of data to build models to

classify people into different groups or predict their behavior . For instance,
we might build a model that
predicts how much of a product we'll sell if we lower (or raise) the price.
While we won't be able to predict WHO will buy at the new price, we really
don't care. We only need to know if we'll sell more at the new price. Thus,
predictive analytics help us determine which marketing strategies will
produce the best ROI (Return on Investment).
How businesses use predictive analytics?
Businesses use predictive analytics in a number of ways, one such way is
discussed above. In addition, a number of tools, such as CRM (Customer
Relationship Management) use predictive analytics to determine marketing
strategies. Another type of predictive analytic is CLV (Customer Lifetime
Value) which uses purchase information to classify customers into groups
and determine the level of profit reflected by each group, which is used to
build marketing strategies for each group.
Descriptive models and predictive analytics
Descriptive models are often overlooked as tools for generating predictive
analytics because they suggest strategies that will generate better results
without being able to quantify how much better the results will be.
6
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
Source: griibdesign.co.uk
An example is the TRA (Theory of Reasoned Action). This model states that
buying behavior is impacted by a consumers attitude and beliefs about the
products, as well as the norms related to that purchase. This theory,
ofcourse, underpins how social media works. Social media helps in building
attitude

toward products, based on the references from the most credible sources -
our friends – and establishes norms of behavior when we see all our friends
buying the product. So, why aren't these descriptive models being used
more frequently in businesses? In part, that's due to poor exchange between
businesses and
academics ,who seem to speak different languages.
Predictive analytics and social media
Social media analytics is a powerful tool for uncovering customer sentiment
dispersed across the countless online sources. As businesses feel the
pressure
to gain new insights from social media, they require the analytics expertise
to transform this flood of information into actionable strategies.
There is a lot of internet chatter about social media analytics to predict
the future. This field of predictive analytics is in its infancy, but there has
been enough success to generate excitement about its potential.
7
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
In case of social commerce, any kind of buzz is a good buzz because it
directly translates into customer demand. For example, keeping tap of all
the trending topics on Twitter can be a useful exercise to predict future
demands. This allows business to leverage social media and maximize sales.
Though the concept is still in its infancy, 2013 is an exciting time where we
could see some of these concepts being implemented.
8
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social

Media
Beyond Sentiments
Zishan Ansari
Zishan is a SAS certified predictive modeler with over 4 years' analytics consulting experience for global players
in banking, insurance and retail domain. Zishan is currently part of Target Corporation's enterprise business
intelligence team based in India that provides analytic solutions to problems in operational risk, loss prevention
and profit protection area.
9
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
Beyond Sentiments
Zishan Ansari - Senior Business Analyst, Target Corporation
Source - />If you are reading this, you probably are aware of how things in the social
media world usually work. You probably have used/seen/heard of tools that
tells you about the sentiment of your customers, by analyzing what they are
writing over various social media platforms. And I am sure many of you
would have also seen software providers making tall claims about how
accurate their engines are in predicting the correct sentiment of a
company’s customer base. There is no question about whether sentiment
analysis is a powerful analysis technique or not, because it certainly is. The
bigger question is whether it is the right thing for you or not? And if it is,
then do you have the ability to apply it correctly or not?
If you are looking for an answer to the question whether investment on
sentiment analysis is the right thing for your business, then read further. In
case you have already spent loads of cash on buying a sentiment analysis
package, still read further to know how you can best utilize it.
Why sentiments?
Being a part of a smart and proactive organization that listens to all its

customers, you would want to build a strategy where you:
· Listen to all that your customers are saying about your brand or a
newly launched product
· Take actions based on customer sentiments
· Redress customer grievances by offering him or her some brownie
points
· And in turn be loved by your customers for being a great listener
10
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
Well, this all works really well when you are running a ‘Mom and Pop Store’.
Why? Because:
· You know who your customers are
· You understand their language
· You understand their moods, their emotions
· You know their preferences
· You know what will please/displease them

How are things different in social media?
Simple answer to this would be – in more ways than one. It is important for
you to understand these differences to figure out whether you need
sentiment analysis or not. .
Not every person is good in expressing themselves in text, and definitely not
in just hundred and forty characters. And this poses a big challenge.
Why? Because, there is no way to capture customer’s facial expression
through social media, nor is there a way to capture voice modulation to
figure out customer’s mood.
With deliberately excluding the discussion about misclassifications that

majority of the tools anyways do, there is one more aspect of language that
I think should be considered, and that is dialects. In this very world of ours,
where spoken languages change with every two hundred to three hundred
kilometers, it will only be illogical for us to expect everyone to express their
11
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
sentiments in the language in which our software’s NLP engine is trained.
OK. So in that case will it be insane for us to demand for an NLP engine that
has the functionality of identifying the sentiments from any
language/dialect. No, it wouldn’t be completely insane. But it is very likely
that you will be paying a bomb to get such a service.
Let us assume that you get an NLP engine that has all these powers. Tell
me who writes a perfect language these days? If you think your customer
does, then you are absolutely wrong. Even Shakespeare would have had a
hard time in expressing himself in hundred and forty characters forget about
an average Joe (Pardon me if you are Shakespeare or Joe!). We are living in
an era where even native speakers are getting bad in grammar day by day.
Languages are evolving, and so are the NLP engines. And, more evolved an
engine is, more dollars you have to burn for it.

Knowing your objective
You will be solving the major part of the puzzle if you figured out what your
objective is behind sentiment analysis. Because, after this you just have to
pick the right approach to achieve your goal.
If you are managing a customer service center and you receive 100,000 e-
mails every day, and would like them to be classified as Positive, Neutral or
Negative then you can use software that has the capability to do the job.

That’s all the functionality you need to achieve your goal. Rest of the work
will be done by the executives to ensure each customer is satisfied.

Looking beyond sentiments
Say if you had kids. You find out on a Sunday morning that your kids were
annoyed about something and were not looking happy. Being a good parent
you give them permission to go out with friends. If you are a more involved
parent, you would yourself go out with your kids, to make their day. A
12
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
parent very well knows what to do to change the mood of their kids.
As a kid I have really enjoyed that. Sometimes getting annoyed for no good
reason can also get you treats, just because your parents wants you to be
happy always.
But if you were a responsible parent, what else would you do? You would
probably try to understand, why were your kids upset at the first place?
Have they been getting annoyed quite often recently? What are the
circumstances which makes them unhappy?
A responsible company is no different from a responsible parent in this
aspect. It will do a root cause analysis of what actions led to all this. And
they can take actions to ensure that such circumstances do not arise in
future. An organization with a dedicated customer service team can
probably do all what a responsible parent do, given that they know who the
customer is. It can spend resources to get in touch with the customer,
understand his/her concerns, identify the causes of unhappiness and then
act accordingly. It can also go ahead and analyze what were the things that
led to such circumstances.

So what should you do? Should you wait for a cheaper NLP engine with all
the functionality? Or should you wait until your company buys a foolproof
text-analytics software license?
It is important to be clear about what exactly is your objective to perform
sentiment analysis. You can then combine the results from a not so very
expensive tool with other free tools or with your own data visualization
tools for analysis.
Stream Graphs
One such freely available tool is stream graph. It helps you in analyzing
what people have been tweeting about a brand/product over a period of
13
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
time.
Figure: (Source - />The Stream Graph shows the usage over time for the words, which are
highly associated with the search word. One of these series together with a
time period is in a selected state and colored red. The tweets that contain
this word in the given time period are shown below the graph. You can click
on another word series or time period to see different matches. In the
match list you can click on any word to create a different graph with tweets
containing that word. You can also click on the user or comment icons and
any URL to see the appropriate content in another window. If you see a
large spike in one time period that hides the detail in all the other periods it
will be useful to click in the area to the left of the y-axis in order to change
the vertical scale.
The bad part is that the free version analyzes latest thousand tweets. The
good part is that there are open source resources
( available to help you develop such graphs.

Probably you need to invest some time to develop that. Remember, there
are no free lunches and there are no free graphs either.
14
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
You can combine the results of the sentiment analysis with the
results of stream graph analysis to infer what circumstances
probably led to positive or negative sentiments. So even if your
sentiment analysis says that 80% of your customers have neutral
opinion and your sales figures are way below your forecasted sales,
a stream graph can help you identify what probably is causing the
low sale. Stream graphs present one way of visualizing the data.
There can be multiple such ways of analyzing it.
A good analyst will always find a suitable way of presenting the
appropriate information that you would like to have in order to
validate your sentiment analysis findings. And remember without
validation, your results from sentiment analysis in the worst case
can be as bad as that from a random classifier.
15
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
Social Media Strategies for
the Data Driven Newsroom
Dennis Mortensen
Dennis Mortensen is CEO & Founder of Visual Revenue, Inc., whose Editorial Support Platform helps editors to
better place content and provides real-time recommendations and predictive analytics to more than 250 global

online publishers, including Comcast, The Atlantic, NBC Universal and Le Monde. He is the author of Data Driven
Insights from Wiley and sits on the Board of the Digital Analytics Association.
16
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
Social Media Strategies for the Data Driven Newsroom
Dennis Mortensen – CEO, Visual Revenue
Just as the Internet itself began to upend news and journalism in the mid-
1990’s, so too has social media added another layer to that upheaval.
Perhaps even a greater one that doesn’t just change the delivery and
consumption of news and information, but the creation and molding of the
stories themselves. To compare the changes, it would be one very large
order of magnitude.
Social Media: Newswire or Newsroom
It’s agreed that the prevalence of mobile devices and social media tools has
turned everyone into a publisher of sorts. While not every individual can
hope to monetize their tweets like a celebrity, every last tweet out there
has the potential to affect journalists and the gathering of news. They may
not lead the story, but they’ve become parts of the stories told (man
tweeting Bin Laden raid) and parts of the newsgathering process (Egypt and
the Arab Spring).
In the 24 months since Andy Carvin of NPR provided a model for futuristic
newsgathering by tweeting at potential sources and confirming reports from
afar, many, if not most, journalists have found their way onto Twitter and
are using it to the same effect.
In the same short span, this same move to the center of the news has
happened in the newsrooms themselves in the way that content is pushed
out to an audience. The Social Media Editor’s role was created to

evangelize and educate. With so many journalists of all stripes now savvy in
social, it has become critical to determine and assign both ownership of the
social channel within the newsroom, as well as ownership of the content
that goes out under each individual feed.

Defining Success in Editor and Publisher Terms
17
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
As more and more people in the newsroom have moved to publishing on the
many social platforms available to them, the movement to measure that
activity has followed. For most individuals, a somewhat limited view of
success in social media is defined simply by response. Did I get re-tweeted?
Favorited? How many @ replies do I have? What’s my Klout score?
This level of measurement is fine for the individual, but not for media
companies – where activity must be measured by the way it delivers
audience, and by how that audience ultimately can be monetized.
For online properties, if you want to increase your audience, that content
must be exposed to new audiences on a regular basis. Publishers
understand this, and most quickly go to Facebook, Twitter or other social
media channels to expand their reach.
Yet the true impact on their business – success or failure – is very difficult to
measure. Sure, they can measure tweets and favorites
and likes and other vanity metrics. It’s easy and
can be a trap that is fallen into quickly. But re-
tweets and favorites and shares only have a
secondary effect upon the business, and they
hardly measure audience interaction.

The editors in large newsrooms of leading editorial operations need to know
more. Just as with the content and activity on their own websites and
properties, they want and need to measure social media similarly.
For example, what are the expectations of content published? If editors at
The Atlantic, publish a piece of content at 1pm, it would be fair to have an
expectation on how much direct output it will generate:
• How many views should this content generate?
• How many views does it actually receive?
• Is this content that should be shared on social media?
18
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
• If so, when should it be shared to attain the maximum impact?
As a process, editors and their social media tools should essentially follow a
process of (1) finding and selecting the proper content; (2) pushing that
content into the social channels; (3) measuring success and/or failure, and
(4) learning and optimizing from it.
When editors begin to answer these questions and follow this process, they
make the definition of their success in social media more precise, and they
move away from the vanity metrics of the consumer marketplace. It is one
of the things that separate the genuine publishers from the “everybody’s a
publisher” publishers.

Determining Success and Failure in Real Time
The real-time nature of social media interaction makes it a natural
complement to the newsroom. It is, however, that same fleeting aspect that
makes real-time success measurements akin to capturing lightning in a
bottle for them. It can only be done with some of today’s more

sophisticated tools.
With the proper tools in hand, news organizations can have more exact
measurements on social media. For example, they can have a means to
determine the difference between tweeting content at 4:23 p.m. and 4:35
p.m., followed by recommended actions based on real-time performance
and consumption data. Additionally, the best tools can tell editors whether
19
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
or not to include photos when sharing or tweeting, which accounts to share
on, and sometimes, the value of sharing specific content multiple times.
This difference can be significant for some properties versus others.
Patterns for when and what to share exist, but they tend to be very much
property-specific. They are so specific that, for example, one news
organization can share content with equally powerful results from dawn ‘til
dusk, while another will only succeed in limited windows. What works for
one news organization won’t work for another, largely as a result of
audience fragmentation having intensified to the degree it has.
Figure 1: Historic Success Measurement for Leading Online Properties
A comparison of activity for two leading online properties, showing hourly clicks
into their article content via social media. Note that one property, in addition
to an overall larger number of clicks per hour, never truly falls to zero, while
the other does so almost every night.
For the editor and the newsroom, this makes their social media activity only
worth the time that they invest in measuring it not for the vanity metrics,
but for the deeper ones. This is where their ability to know true success
from simple failure will show whether their time spent sharing (to grow
their audience) has been well spent.

Using Predictive Analytics to Determine Your Next Step
Editors today, particularly social media editors, live within what can be an
20
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
endless torrent of information, opinions and activity. They are called upon
to quickly whittle it all down, and make quick, yet significant decisions
about the placement and direction of content. Given social media’s real-
time nature, the use of predictive analytics can help data-driven editors to
stay one step ahead of the game.
Figure 2: Benchmark Performance Predicted for Two Leading Online
Properties (24-hour period)
A comparison of the expected social media activity for two leading online
properties, showing hourly clicks into their article content via social media.
Note that one property, carries a consistently higher level of activity that (a)
peaks more sharply during key periods, and (b) maintains a significant level of
inbound clicks (views) throughout the overnight period.
Whereas these decisions were once made based on intuition, skill and
instinct, there now exists a huge pool of data that, when properly applied,
can enhance an editor’s judgment with suggestions and the additional
confidence to take decisive action.
The genuine value of such predictive algorithms is in the ability to
recommend specific actions for an editor within an editorial framework
outlined by the organization. Separately, these two elements are
important; together, they provide a powerful engine for editors to act
immediately, secure in both their judgment and the interest of their
publication.

These new tools simplify data and tell a newsroom when it should tweet and
also what it should be tweeting. The computerized suggestions take on the
21
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media
role of a deputy editor: someone who knows the history of the data, as well
as editorial values of the paper, and can therefore determine the best
publishing strategy to follow.
In the end, it is still the editor making judgment calls. They just happen to
be faster and better calls.

Conclusion
Today’s data-driven newsroom relies on many tools to keep pace with the
real-time nature of communications. Social media is a natural fit for the
newsroom, both in the collection and dissemination of the news, but it
needs to be deployed within a editorial framework. Without one, the
publisher may as well be an individual. But with a clearer, data-driven
strategy for measuring the success and failure of the outbound social media,
the newsroom of today will be ready for the news of tomorrow.
22
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media

23
World’s First 360° Social Marketing Suit
www.simplify360.com

Simplify360 eBook: Predictive Analytics The Future of Social
Media
Too much talk in Analytics &
too little action!
Ajay Kelkar
Ajay Kelkar, Co-Founder & COO of Hansa Cequity, has over 20 years of experience in customer-driven marketing
across a wide range of industries like Soft goods, Banking & Financial services & Retail. He has had exposure to a
wide variety of business styles & cultures across Procter & Gamble, Britannia, Marico, Shopper’ Stop & HDFC
bank.
Too much talk in Analytics & too little action!
Ajay Kelkar – COO, Hansa Cequity
Is analytics yet another fad? Is there much more talk about it than real
solid action. It does seem so when you look around you as a consumer.
Marketers still don’t care, as much, about being relevant to you. You get
that umpteenth credit card solicitation from the bank which has already
sold you a card. And nothing about a physical Retailer shopping experience
makes it personal for you!
And yet your online persona seems to be treated differently & when you go
to Amazon & other sites you do get a feeling of getting offers being
recommended for you. And as a consumer you flit between your online &
offline avatars & this becomes more & more obvious.
What’s the difference? Is there a category of organization which is able to
leverage “data” far more effectively?
Gartner says that only 20% of enterprise will use more than 50% of the total
data they collect to gain competitive advantage.
24
World’s First 360° Social Marketing Suit
www.simplify360.com
Simplify360 eBook: Predictive Analytics The Future of Social
Media

This is what software architect Grady Booch had in mind when he uttered
that famous phrase: "A fool with a tool is still a fool."
Google-executive-turned-Yahoo-CEO-thought-leader Marissa Mayer
declares "data is apolitical" and that her old company succeeds because it is
so data-driven: "It all comes down to data. Run a 1% test [on 1% of the
audience] and whichever design does best against the user-happiness
metrics over a two-week period is the one we launch. We have a very
academic environment where we're looking at data all the time. We
probably have somewhere between 50 and 100 experiments running on live
traffic, everything from the default number of results to underlined links
to how big an arrow should be. We're trying all those different things."
A recent Ad Age article carried this comment:
British Airways spent almost a decade corralling passenger data from 200
sources into one database. It built infrastructure to support the number
crunching, but perhaps the harder piece, said Simon Talling-Smith, exec
25