I have a series of monthly surveys asking for services perception and I can use logistic regression to build a model every month to predict the probabilities and the associated lift. My question is: How should I approach the challenge of tracking my lift levels over time? Should I build a new logistic model every month and compare the resulting lift for each monthly model, should I use a constant model and apply it to each month and then track the resulting lifts, or is there another way to do this? PS: same variables need to be preserved in the model for comparison.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.