A PREDICTIVE ANALYTICS

PRIMER
ANALYSIS OF ARTICLE BY THOMAS H. DAVENPORT
WHAT IS PREDICTIVE
ANALYTICS?
A WAY TO PREDICT THE FUTURE
USING DAYA FROM THE PAST.
EXAMPLES
CUSTOMER LIFETIME VALUE(CLV): PREDICTING HOW MUCH A
CUSTOMER WILL BUY FROM THE COMPANY OVER TIME.

ANALYTICAL PREDICTION OF THE PRODUCT OR SERVICE THAT THE

CUSTOMER IS MOST LIKELY TO BUY NEXT.

DIGITAL MARKETING MODELS TO DETERMINE WHAT AD TO

PLACE ON WHAT PUBLISHER’S SITE.

PERFORMING A SALES FORECAST.

KEY INSIGHTS
 “
The quantitative analysis isn’t magic—but it is
normally done with a lot of past data, a little
statistical wizardry, and some important
assumptions.

”
DATA
Lack of good data is If you have multiple
channels or customer
the most common
touchpoints, you need to
barrier to make sure that they
organizations capture data on customer
seeking to employ purchases in the same way
predictive analytics. your previous channels
did.
STATISTICS
Regression analysis in its various forms is the primary tool that organizations use
for predictive analytics.

The analyst performs a regression analysis to see just how correlated each
variable is; this usually requires some iteration to find the right combination of
variables and the best model.

It’s quite likely that the high scoring customers will want to buy the product—
assuming the analyst did the statistical work well and that the data were of good
quality.
ASSUMPTIONS
The big assumption
in predictive
analytics is that the
future will
continue to be like
the past.
 WHAT MAKES ASSUMPTIONS
INVALID?
TIME:
If your model was created If the analyst didn’t
several years ago, it may no include a key variable in
longer accurately predict the model, and that
current behaviour. The
variable has changed
greater the elapsed time, the
more likely customer substantially over time.
behaviour has changed.
CASE IN POINT: FINANCIAL CRISIS 2008
RELEVANCE TO A MANAGER
IN INDIA
A MANAGER SHOULD SEEK THE
ASNWER OF THE FOLLOWING
QUESTIONS FROM HIS TEAM OF
DATA ANALYSTS:
 Can you tell me something about the source of data you
used in your analysis?

 Are you sure the sample data are representative of the

population?

 Are there any outliers in your data distribution? How did

they affect the results?

 What assumptions are behind your analysis?

 Are there any conditions that would make your

THANK YOU!!
BY: TARANG JAIN