Machine-Learning Models for Customer-Behavior Analytics: A Review

Haixiang Sun

doi:10.47297/taposatWSP2633-456905.20250606

PDF
导出
分享
收藏
专辑

Machine-Learning Models for Customer-Behavior Analytics: A Review

6卷第6期

浏览量: 0 Downloads: 0

Machine-Learning Models for Customer-Behavior Analytics: A Review
Machine-Learning Models for Customer-Behavior Analytics: A Review
School of AI and Advanced Computing, XJTLU Entrepreneur College (Taicang), Xian Jiaotong-Liverpool University, Suzhou Jiangsu, 215400, China
2025年6卷第6期页码：24-29
纸质出版日期：2025-06-30
DOI：10.47297/taposatWSP2633-456905.20250606
Accepted：

Scan QR Code

(2025). Machine-Learning Models for Customer-Behavior Analytics: A Review. 科技理论与实践（英文版）, 6(6), 24-29.

Sun Haixiang.Machine-Learning Models for Customer-Behavior Analytics: A Review[J].Theory and Practice of Science and Technology,2025,06(06):24-29.
(2025). Machine-Learning Models for Customer-Behavior Analytics: A Review. 科技理论与实践（英文版）, 6(6), 24-29. DOI： 10.47297/taposatWSP2633-456905.20250606.

Sun Haixiang.Machine-Learning Models for Customer-Behavior Analytics: A Review[J].Theory and Practice of Science and Technology,2025,06(06):24-29. DOI： 10.47297/taposatWSP2633-456905.20250606.

摘要

Abstract

Customer-behavior analytics has rapidly evolved with the advent of machine learning

enabling businesses to predict and influence customer actions. This review surveys recent machine-learning models applied in customer-behavior analytics

including predictive models for churn

lifetime value

and purchase behavior

as well as clustering techniques for customer segmentation. We compare the performance of different approaches (from simple classifiers to deep learning and ensemble methods) and discuss their relative strengths and weaknesses. A key theme is the trade-off between model complexity and interpretability: while advanced models can improve accuracy

their opaque nature raises concerns addressed by explainable AI. We also identify practical challenges in deploying these models

such as data quality

class imbalance

and evolving consumer trends. Finally

we outline future research directions

highlighting the need for hybrid modeling techniques and improved interpretability to build more trustworthy and effective customer analytics systems.

关键词

Keywords

references

B. Prabadevi, R. Shalini, and B. R. Kavitha, Customer churning analysis using machine learning algorithms [J ] .International Journal of Intelligent Networks, vol. 4 , pp. 145 – 154 , 2023 .

H. H. Chang and A. Mukherjee, Machine learning and consumer data [J ] .arXiv preprint arXiv: 2306.14118 , 2023.

J. Du, Predictions for consumer behaviour of e-commerce sales data 2023–2024 based on the LightGBM model [J ] .In Proceedings of the 1st international conference on e-commerce and artificial intelligence (ECAI 2024), Beijing, China: Science; Technology Publications, 2024, pp. 109 – 116 .

Z. Chen, The investigation of machine learning approaches for customer segmentation, in Proceedings of the 1st international conference on e-commerce and artificial intelligence (ECAI 2024). [J ] .South Bridge, Edinburgh, U.K.: Science; Technology Publications, 2024, pp. 71 – 76 .

A. M. Haddadi and H. Hamidi, A hybrid model for improving customer lifetime value prediction using stacking ensemble learning algorithm [J ] .Computers in Human Behavior Reports, p. 100616 , 2025 .

M. Geetha and D. Karthika Renuka, Deep learning architecture towards consumer buying behaviour prediction using multitask learning paradigm [J ] .Journal of Intelligent Fuzzy Systems, v ol. 46 , no. 1 , pp. 1341 – 1357 , 2024 .

J. M. John, O. Shobayo, and B. Ogunleye, An exploration of clustering algorithms for customer segmentation in the UK retail market [J ] .Analytics, vol. 2 , no. 4 , pp. 809 – 823 , 2023 .

B. A. Maulana and N. Hidayati, Churn prediction in credit customers using random forest and XGBoost methods [J ] .Indonesian Journal of Data and Science, vol. 6 , no. 1 , pp. 81 – 89 , 2025 .

S. Ali et al., Explainable artificial intelligence (XAI): What we know and what is left to attain trustworthy artificial intelligence [J ] .Information fusion, vol. 99 , p. 101805 , 2023 .