Prerequisite: This course assumes a familiarity with data and databases.
This one-day class is designed for people who are familiar with data and databases, but unfamiliar with the modeling techniques used to perform important tasks such as scoring customers for likelihood to make a purchase, likelihood to default, channel affinity, and expected remaining lifetime.
This class takes the point of view that a model is simply a formal description of relationships that exist in data. Good formal descriptions have many uses. A good description of a profitable customer can be used to classify new customers as likely or unlikely to be profitable by measuring their distance from the prototypical profitable customer. A good description of who has responded to past offers can be used to predict who will respond to future offers. A model may take the form of a set of rules or a mathematical formula. Either way, it can be tested for stability and accuracy so that it can be applied with confidence. The class will teach you what it takes to build stable models that remain effective for a long time and generalize well to new data sets.
Several popular modeling techniques will be introduced and demystified, including decision trees, contingency tables, and linear regression. These techniques will be applied to real data from a real product penetration case study. By studying the same business problem using several different modeling techniques, the class teaches a modeling methodology appropriate for all models, while demonstrating the particular strengths of modeling approaches.
You Will Learn
- How models help turn data into information
- The difference between descriptive and predictive models
- When to have confidence in a model’s predictions
- How several popular modeling techniques, including decision trees and regression models, actually work
Geared To
- Data analysts; business analysts; marketing analysts; anyone with lots of data and not enough information