Reference: Berry, M.J.A. and Linoff, G.S., Mastering Data Mining, Wiley: New York, 2000.

Two Styles of Data Mining

1. Directed Data Mining:

2. Undirected Data Mining:


The Virtuous Cycle of Data Mining

Consists of four major business processes (success in data mining requires all four):

virtuous cycle


1. Identify the Business Problem

Business people's expertise allows you to answer the following questions:

Checking the opinion of domain experts:


2. Transforming Data into Actionable Results

Data Mining

Identify and obtain data

Validate, explore and clean the data

Transpose the data to the right granularity

Add derived variables

Prepare the model set

Choose the modeling technique and train the model

Check performance of the models


3. Acting on the Results


4. Measuring the Model's Effectiveness


What Makes Predictive Modeling Successful?

Time frames of predictive modeling:

Shelf-life of a Model

Key assumptions of predictive modeling:

1. The Past Is a Good Predictor of the Future

2. Adequate Data Are Available to Form a Model