Customer churn prediction for web browsers

作者：

Highlights：

• We propose the Multivariate Behavior Sequence Transformer for churn prediction.

• We combine static and dynamic data for informative knowledge of user behavior.

• We conduct extensive experiments to demonstrate the superiority of our approach.

摘要

•We propose the Multivariate Behavior Sequence Transformer for churn prediction.•We combine static and dynamic data for informative knowledge of user behavior.•We conduct extensive experiments to demonstrate the superiority of our approach.

论文关键词：Churn prediction,MBST,Attention mechanism,Tree-based models,Sequence models

论文评审过程：Received 16 December 2021, Revised 15 June 2022, Accepted 14 July 2022, Available online 25 July 2022, Version of Record 1 August 2022.

论文官网地址：https://doi.org/10.1016/j.eswa.2022.118177