Predicting B2B Customer Churn and Measuring the Impact of Machine Learning-Based Retention Strategies

Victória Emanuela Alves Oliveira, Victória Emanuela Alves Oliveira, Amanda Cristina da Costa Guimarães, Arthur Soares de Quadros, Arthur Soares de Quadros, Reynold Navarro Mazo, Reynold Navarro Mazo, Rickson Livio de Souza Gaspar, Alessandro Vieira, Wladmir Brandão, Wladmir Brandão

2025

Abstract

Acquiring new customers often costs five times more than retaining existing ones. Customer churn significantly threatens B2B companies, causing revenue loss and reduced market share. Analyzing historical customer data, including frequency on product usage, allow us to predict churn and implement timely retention strategies to prevent this loss. We propose using Support Vector Machines (SVMs) to predict at-risk customers while retraining it, if necessary. By monitoring its recall over 15-day periods, we retrain the model if its recall on new data falls below 60%. Our research focuses on feature selection to identify key churn factors. Our experiments show that when constantly retraining the model, we avoid accuracy loss by updating the customer’s context, providing valuable insights on how to reduce churn rates and increase revenue.

Paper Citation

in Harvard Style

Oliveira V., Guimarães A., Soares de Quadros A., Mazo R., Gaspar R., Vieira A. and Brandão W. (2025). Predicting B2B Customer Churn and Measuring the Impact of Machine Learning-Based Retention Strategies. In Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS; ISBN 978-989-758-749-8, SciTePress, pages 572-581. DOI: 10.5220/0013436300003929

in Bibtex Style

@conference{iceis25,
author={Victória Oliveira and Amanda Guimarães and Arthur Soares de Quadros and Reynold Mazo and Rickson Gaspar and Alessandro Vieira and Wladmir Brandão},
title={Predicting B2B Customer Churn and Measuring the Impact of Machine Learning-Based Retention Strategies},
booktitle={Proceedings of the 27th International Conference on Enterprise Information Systems - Volume 1: ICEIS},
year={2025},
pages={572-581},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013436300003929},
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 - Predicting B2B Customer Churn and Measuring the Impact of Machine Learning-Based Retention Strategies
SN - 978-989-758-749-8
AU - Oliveira V.
AU - Guimarães A.
AU - Soares de Quadros A.
AU - Mazo R.
AU - Gaspar R.
AU - Vieira A.
AU - Brandão W.
PY - 2025
SP - 572
EP - 581
DO - 10.5220/0013436300003929
PB - SciTePress