Terminology
- Lift Curve is one of the visual aids for measuring model performance. Lift is a measure of the effectiveness of a predictive model calculated as the ratio between the results obtained with and without the predictive model. A lift in a given decile is calculated as the
Lift(i) = P(target var=1 | decile i)/ P(target var=1) - 1
The higher spread among the deciles, the better predictive value is from the model.
