Identifying Bot-Driven Purchase Activities Using Machine Learning Techniques

Abstract

The rapid growth of e-commerce platforms has increased the prevalence of automated threats such as bot-driven purchase activities. These bots exploit online marketplaces by executing high-frequency transactions, manipulating product availability, and generating fraudulent purchasing behavior. Traditional rule-based detection systems are often ineffective in identifying sophisticated bots that mimic human interactions. This study proposes a machine learning-based framework for detecting bot-driven purchasing activities in e-commerce environments. The proposed approach integrates behavioral feature engineering, transactional analysis, and supervised machine learning classification to distinguish automated bots from legitimate users. Multiple algorithms, including logistic regression, decision trees, random forests, gradient boosting, and deep neural networks, were evaluated using standard performance metrics such as accuracy, precision, recall, and F1-score. Experimental results demonstrate that ensemble learning techniques and deep neural networks achieve superior detection performance due to their ability to capture complex behavioral patterns. The findings highlight the importance of integrating artificial intelligence into e-commerce security systems to improve fraud detection capabilities. The proposed framework provides a scalable and adaptable solution for identifying automated purchasing activities and protecting digital marketplaces from fraudulent behavior.