An Intelligent Data Mining Model for Phishing Detection in E-Commerce Platforms

Abstract

Phishing attacks have emerged as a significant cybersecurity threat to e-commerce platforms, targeting users to obtain sensitive information such as login credentials, banking details, and financial records. Existing machine learning and deep learning approaches often suffer from limitations related to redundant features, inefficient feature representation, and reduced generalization capability in dynamic phishing environments. To address these challenges, this paper proposes an intelligent data mining model for phishing detection in e-commerce platforms. The proposed framework integrates feature selection and embedding-based representation learning to capture meaningful patterns from phishing-related data and improve classification performance. Experimental evaluation demonstrates strong detection capability, achieving 93.93% accuracy with balanced precision, recall, and F1-score, along with an AUC of 0.984. The results confirm the robustness, reliability, and practical applicability of the proposed framework for enhancing security and trust in modern e-commerce systems.