Explainable and Optimized Random Forest Model for Customer Purchase Prediction and Segmentation in E-Commerce

DOI

10.2991/978-94-6239-664-7_91How to use a DOI?

Keywords

Random Forest; Explainable AI; Customer Segmentation; Purchase Prediction; E-Commerce

Abstract

Finding the correct customer purchase prediction and crossapplicable segmentations will improve personalization and ultimately grow revenue within e-commerce. Current and traditional machine learning paradigms struggle to recognize the behavior of people as a non-linear and complex phenomenon that lacks clarity in terms of actionable insights for businesses. The current study proposes and implements an understandable and optimized Random Forest framework used to predict customer purchases and segment online shoppers based on sessionlevel behavioral features. The proposed procedure includes addressing class imbalance through the inclusion of SMOTE, tuning hyperparameters using GridSearchCV, and performing a SHAP analysis to explain feature attribution and generate insight. Extensive experiments using real-life scenarios from an e-commerce data set demonstrate that the tuned random forest achieves a verifiably accurate AUC of 99.15%, surpassing some common baseline models. The use of K-Means clustering supports meaningful customer segments and actionable customer relationship targeting and retention strategies. The results substantiate the premise that a model combining performance with explainability as well as strong segmentations has the potential to become useful for datadriven personalization in modern e-commerce environments.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Md. Nazmul Alam Chowdhury
AU  - Md. Nazrul Islam Mondal
AU  - Nitun Kumar Podder
AU  - Md. Siam Uddin Molla Antor
AU  - Md Habibul Islam
PY  - 2026
DA  - 2026/06/08
TI  - Explainable and Optimized Random Forest Model for Customer Purchase Prediction and Segmentation in E-Commerce
BT  - Proceedings of the International Conference on Intelligent Data Analysis and Applications (IDAA 2025)
PB  - Atlantis Press
SP  - 1347
EP  - 1361
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-664-7_91
DO  - 10.2991/978-94-6239-664-7_91
ID  - Chowdhury2026
ER  -