Cluster-Guided Machine Learning Models for E-Commerce Customer Behavior Prediction

DOI

10.2991/978-94-6463-823-3_74How to use a DOI?

Keywords

K-means Clustering; Classification Models; Purchase Behavior

Abstract

E-commerce has gradually become one of the most popular shopping channels nowadays, as a result of its convenience and efficiency. Although online shopping is developing significantly fast, a low conversion rate is still a problem among various platforms and businesses. Aiming at dealing with such a gap, this study endeavors to predict customers’ heterogeneous decision-making processes more comprehensively by applying K-means clustering and four classification models, which involve Random Forest, Extreme Gradient Boosting (XGBoost), Logistic Regression, and Support Vector Machine (SVM). Before clustering, exploratory data analysis (EDA) and principal component analysis (PCA) are applied to understand highly correlated features and components. Three clusters are produced, including high-value customers, potential customers, and churned customers. Page values feature is a significant consideration for high-value customers, and potential consumers tend to dwell on informational pages. Churned customers are more likely to focus on November, which has a certain correlation with a special day. The findings reveal that XGBoost is the “best” model for both high-value customers and churned customers. For potential customers, Random Forest performs the highest F1-score. Additionally, Voting Classifier is also conducted to boost overall performance. This study not only offers tailored models for each consumer group to promote the purchase prediction process but also provides practical insights for real-time personalized marketing strategies.

Copyright

© 2025 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  - Zhenmei Jin
PY  - 2025
DA  - 2025/08/31
TI  - Cluster-Guided Machine Learning Models for E-Commerce Customer Behavior Prediction
BT  - Proceedings of the 2025 3rd International Conference on Image, Algorithms, and Artificial Intelligence (ICIAAI 2025)
PB  - Atlantis Press
SP  - 753
EP  - 760
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-823-3_74
DO  - 10.2991/978-94-6463-823-3_74
ID  - Jin2025
ER  -