Last week we looked at several metrics for assessing the performance of classification models – accuracy, receiver operating characteristics (ROC) curves, and lift (gains). In this week’s Brief we move beyond lift and cover uplift.
Our course spotlight again is:
- Feb 28 – Mar 27: Persuasion Analytics and Targeting
See you in class!
UpLift and Persuasion
Marketers have long known that different messages to different people work better than one-size-fits-all. The statistical models that guide differentiated messages are termed […]
Word of the Week
Predictor P-Values in Predictive Modeling – Not So Useful
Predictor p-values in linear models are a guide to the statistical significance of a predictor coefficient value – they measure the probability that a randomly shuffled model could have produced a coefficient as great as the fitted value. They are of limited utility […]
Case Study
Second Opinions
Should employers or insurers require second opinions as a way to reduce disability costs? Read this Elder Research case study of how multiple analytic techniques were brought to bear on this problem.
Course Spotlight
Feb 28 – Mar 27: Persuasion Analytics and Targeting
Your instructor is Ken Strasma, director of targeting for the Kerry and Obama presidential campaigns, and co-founder and CEO of HaystaqDNA, a firm that provides predictive analytics and strategic consulting services for corporations, non-profits and membership organizations.
In this course you will learn how to:
- Find voter/customer targets that are appropriate to a campaign phase
- Design a survey instrument for use in a predictive model
- Conduct an A-B test
- Implement predictive models with voter data
- Add uplift modeling to predict whether a person responds better with a “treatment”
See you in class!
