Churn Prediction with Sequential Data and Deep Neural Networks. A Comparative Analysis
Abstract
Off-the-shelf machine learning algorithms for prediction such as regularized logistic regression cannot exploit the information of time-varying features without previously using an aggregation procedure of such sequential data. However, recurrent neural networks provide an alternative approach by which time-varying features can be readily used for modeling. This paper assesses the performance of neural networks for churn modeling using recency, frequency, and monetary value data from a financial services provider. Results show that RFM variables in combination with LSTM neural networks have larger top-decile lift and expected maximum profit metrics than regularized logistic regression models with commonly-used demographic variables. Moreover, we show that using the fitted probabilities from the LSTM as feature in the logistic regression increases the out-of-sample performance of the latter by 25 percent compared to a model with only static features.
Cite
@article{arxiv.1909.11114,
title = {Churn Prediction with Sequential Data and Deep Neural Networks. A Comparative Analysis},
author = {C. Gary Mena and Arno De Caigny and Kristof Coussement and Koen W. De Bock and Stefan Lessmann},
journal= {arXiv preprint arXiv:1909.11114},
year = {2019}
}