Volume 2 - Issue 2, March - April 2026

Explainable Artificial Intelligence (XAI) has gained significant attention in recent years due to the increasing use of black-box machine learning models in commercial decision-making. In e-commerce platforms, predicting consumer purchase behaviour plays a crucial role in optimising marketing strategies and enhancing customer experience. However, the lack of transparency in traditional AI models limits managerial trust and accountability. This paper proposes an explainable AI-driven framework for consumer purchase prediction that integrates predictive accuracy with interpretability. Machine learning algorithms are employed to analyse consumer behavioural data such as browsing history, purchase frequency, and engagement metrics. Explainability techniques, including SHAP and LIME, are applied to provide human-understandable insights into model decisions. Experimental results demonstrate that the proposed approach improves transparency without compromising performance, thereby supporting ethical and responsible AI adoption in e-commerce decision-making environments.

Madhu Sri S, Sanjay S, Dr.Kumaresan,"Explainable AI-Driven Consumer Purchase Prediction for Transparent E-Commerce Decision Making" International Journal of Advanced Multidisciplinary Research and Educational Development, V2(2): Page(1192-1194) Mar-Apr 2026. ISSN: 3107-6513. www.ijamred.com. Published by Scientific and Academic Research Publishing.