Authors:
Chue Thazin Myint, Tharaphi Zaw, Myint Myat Moe, Aye Myat Thwe, Hlaing Htake Khaung Tin, Anurag Hazarika
Addresses:
Faculty of Information Science, University of Information Technology, Yangon, Yangon Region, Myanmar. Department of Management, 21st Century Open University, Sheridan, Wyoming, United States of America.
Abstract:
The fast development of e-commerce has led to the collection of large amounts of data on customers that can be used for the analysis and prediction of customer purchasing behavior. Machine learning offers effective techniques for discovering patterns in customer behavior and making informed marketing and managerial decisions based on the data. This research compares the efficiency of machine learning methods for predicting customer behavior in e-commerce. This study compares different classification algorithms, including Logistic Regression, Decision Tree, Random Forest, Support Vector Machine, and K-Nearest Neighbors. Data preprocessing includes cleaning, feature transformation, variable encoding, and, when required, scaling. The study assesses algorithm performance using standard measures such as accuracy, precision, recall, F1-score, and confusion matrices. The comparative analysis will help identify the most efficient machine learning method and assess the advantages and disadvantages of each algorithm for predicting customer behavior in e-commerce. Using publicly available data will also allow other researchers and students to reproduce the research results.
Keywords: Customer Behavior; Machine Learning (ML); Classification Algorithms; Logistic Regression; Decision Tree; Support Vector Machine (SVM); Data Preprocessing.
Received on: 25/03/2025, Revised on: 04/06/2025, Accepted on: 21/07/2025, Published on: 05/06/2026
DOI: 10.64091/ATITP.2026.000331
AVE Trends in Intelligent Technoprise Letters, 2026 Vol. 3 No. 2 , Pages: 57-65