A Non-Sequential Representation of Sequential Data for\ud Churn Prediction

Part of book or chapter of book English OPEN
Eastwood, Mark; Gabrys, Bogdan;
(2009)

We investigate the length of event sequence giving best predictions\ud when using a continuous HMM approach to churn prediction from sequential\ud data. Motivated by observations that predictions based on only the few most recent\ud events seem to be the most accurate, ... View more
Share - Bookmark