Using Transformers for B2B Contractual Churn Prediction Based on Customer Behavior Data

Jim Ahlstrand, Jim Ahlstrand, Anton Borg, Håkan Grahn, Martin Boldt

2025

Abstract

In the competitive business-to-business (B2B) landscape, retaining clients is critical to sustaining growth, yet customer churn presents substantial challenges. This paper presents a novel approach to customer churn prediction using a modified Transformer architecture tailored to multivariate time-series data. We suggest that analyzing customer behavior patterns over time can indicate potential churn. Our findings suggest that while uncertainty remains high, the proposed model performs competitively against existing methods. The Transformer architecture achieves a top decile lift of almost 5 and 0.77 AUC. We assess the model’s confidence by employing conformal prediction, providing valuable insights for targeted anti-churn campaigns. This work highlights the potential of Transformers to address churn dynamics, offering a scalable solution to identify at-risk customers and inform strategic retention efforts in B2B contexts.

Paper Citation

in Harvard Style

Ahlstrand J., Borg A., Grahn H. and Boldt M. (2025). Using Transformers for B2B Contractual Churn Prediction Based on Customer Behavior Data. In Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS; ISBN 978-989-758-749-8, SciTePress, pages 562-571. DOI: 10.5220/0013432500003929

in Bibtex Style

@conference{iceis25,
author={Jim Ahlstrand and Anton Borg and Håkan Grahn and Martin Boldt},
title={Using Transformers for B2B Contractual Churn Prediction Based on Customer Behavior Data},
booktitle={Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS},
year={2025},
pages={562-571},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013432500003929},
isbn={978-989-758-749-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS
TI - Using Transformers for B2B Contractual Churn Prediction Based on Customer Behavior Data
SN - 978-989-758-749-8
AU - Ahlstrand J.
AU - Borg A.
AU - Grahn H.
AU - Boldt M.
PY - 2025
SP - 562
EP - 571
DO - 10.5220/0013432500003929
PB - SciTePress