Exploiting time-varying RFM measures for customer churn prediction with deep neural networks

DOI10.1007/S10479-023-05259-9MaRDI QIDQ6589106

Kristof Coussement, Koen W. De Bock, Arno de Caigny, Gary Mena, Stefan Lessmann

Publication date: 19 August 2024

Published in: Annals of Operations Research (Search for Journal in Brave)

zbMATH Keywords

attentionpanel datarecurrent neural networksdeep learningtransformersfinancial servicesLSTMGRUcustomer churnRFMtime-varying features

Mathematics Subject Classification ID

Artificial intelligence (68Txx) Multivariate analysis (62Hxx) Operations research and management science (90Bxx)

Cites Work

• Title not available (Why is that?)
• A new hybrid classification algorithm for customer churn prediction based on logistic regression and decision trees
• Deep learning for credit scoring: do or don't?
• How training on multiple time slices improves performance in churn prediction
• A hierarchical multiple kernel support vector machine for customer churn prediction using longitudinal behavioral data
• ADtreesLogit model for customer churn prediction
• A two-step rejection procedure for testing multiple hypotheses
• The Elements of Statistical Learning

Related Items (1)

Predicting and optimizing marketing performance in dynamic markets

This page was built for publication: Exploiting time-varying RFM measures for customer churn prediction with deep neural networks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6589106)