Transcript Business Intelligence/ Decision Models

Business Intelligence/
Decision Models
CRISP
Learning by association
or problem solving
Time/
Cost
Cumulated Productivity
This Week

CRISP

(Cross Industry Standard Procedure for Data Mining)
CRISP-DM Phases
Source SPSS Inc. 2008
SEMMA (SAS Institute)
CRISP Case Study

A large telecom (XYZ PHONE) has discovered that it is losing
customers at a much higher rate than in previous years.

Reporting through the corporate dashboard (OLAP)has shown
churn rates growing by a large margin last year.
Source SPSS Inc. 2008
Define Business Objectives

Strategic objective definition


Related business goal identification



Decrease customer churn by 1%
Cost-benefit analysis


Retain high value customers
Identify process problems that need to be changed
Clear success factor (metric)


Increase revenues by retaining more customers
Increase revenues by $750,000
Actionable BI objectives

XYZ wants to retain more customers by identifying likely
churners 2 months prior and putting an action in place to
retain them
Source SPSS Inc. 2008
Timeline Example

XYZ’s project: 13 weeks

1 week business understanding
• Involves line of business managers
• Includes better defining high-value and churner definition

3 weeks data understanding
• Involves line of business managers and data experts

5 weeks data preparation
• Heavy reliance on data experts and database administrators

2 weeks modeling (1) and evaluation (1)
• Models developed by data miners and results evaluated by line of business
managers

1 week deployment ?
• Heavy involvement of database administrators

Model deployment entailed setting up a data model for monthly
scoring of customer base with resulting reports feeding a mail
offer
Source SPSS Inc. 2008