Purchase Intention Analysis of Online Shoppers Based on Machine Learning and K-Means Clustering

Qi Jiang

2025

Abstract

With the rapid development of e-commerce, online retailers are faced with the challenge of accurately pushing and retaining customers. This study combines machine learning and K-means clustering technology to analyze and predict online shoppers' purchase intentions using user behavior data. By analyzing a dataset of 12,330 user sessions, the study not only explored the key factors influencing purchase intent, but also used the SMOTE technique to address the category imbalance in the dataset. The study used a variety of machine learning models, including random forests, Extreme Gradient Boosting (XGBoost), and artificial neural networks (ANN), while segmenting users through K-means clustering to identify groups with different purchase intentions. The metrics included accuracy, recall, accuracy and F1 scores. The results show that the random forest model has the best performance in all indexes, especially in the recall rate, showing a strong ability to identify purchase intention. At the same time, through K-means clustering, users are successfully divided into different groups, thus providing a more accurate personalized marketing strategy for the e-commerce platform. This research provides the theoretical basis and practical guidance for the precision marketing of e-commerce platforms.

Paper Citation

in Harvard Style

Jiang Q. (2025). Purchase Intention Analysis of Online Shoppers Based on Machine Learning and K-Means Clustering. In Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE; ISBN 978-989-758-765-8, SciTePress, pages 259-264. DOI: 10.5220/0013686100004670

in Bibtex Style

@conference{icdse25,
author={Qi Jiang},
title={Purchase Intention Analysis of Online Shoppers Based on Machine Learning and K-Means Clustering},
booktitle={Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE},
year={2025},
pages={259-264},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013686100004670},
isbn={978-989-758-765-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 2nd International Conference on Data Science and Engineering - Volume 1: ICDSE
TI - Purchase Intention Analysis of Online Shoppers Based on Machine Learning and K-Means Clustering
SN - 978-989-758-765-8
AU - Jiang Q.
PY - 2025
SP - 259
EP - 264
DO - 10.5220/0013686100004670
PB - SciTePress