Explainable Artificial Intelligence in Anomaly Detection for Threat Management in E- Commerce Platform

DOI

10.2991/978-94-6239-616-6_118How to use a DOI?

Keywords

E-commerce security; fraud detection; account takeover; abnormal behavior analysis; hybrid CNN-LSTM; anomaly detection; real-time monitoring; explainable AI; analyst dashboard; threat intelligence

Abstract

E-commerce platforms are increasingly exposed to diverse cyber threats such as fraudulent transactions, fake reviews, account takeovers, and abnormal user behaviors, all of which compromise security and diminish user confidence. Existing detection mechanisms, primarily based on ensemble methods such as Random Forest and XGBoost, often fail to achieve high predictive accuracy due to their limitations in capturing complex spatio-temporal dependencies. To overcome these challenges, this paper proposes a hybrid deep learning framework that integrates Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) networks. CNN is employed for internal spatial feature extraction, while LSTM is leveraged for modeling sequential and temporal dependencies, thus enabling the system to identify nuanced anomalies in user behavior and transaction patterns. The framework supports real-time threat monitoring, ensuring immediate detection of fraud, account takeovers, and abnormal behaviors, while providing interpretable reasoning for flagged anomalies. An interactive analyst dashboard is further introduced to visualize anomalies, risk scores, and feature importance, enabling human-in-the-loop feedback for continuous system refinement. By combining hybrid modeling, explainability, and analyst-driven feedback, the proposed approach significantly improves accuracy, reduces false positives, and strengthens trust in automated decision-making. Experimental validation demonstrates its potential to enhance resilience and operational security in modern e-commerce ecosystems.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - V. Keerthan
AU  - S. Subhiksha
AU  - R. Dhatchayini
AU  - S. B. Shamshira
PY  - 2026
DA  - 2026/03/31
TI  - Explainable Artificial Intelligence in Anomaly Detection for Threat Management in E- Commerce Platform
BT  - Proceedings of the International Conference on Artificial Intelligence and Secure Data Analytics (ICAISDA 2025)
PB  - Atlantis Press
SP  - 1668
EP  - 1678
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-616-6_118
DO  - 10.2991/978-94-6239-616-6_118
ID  - Keerthan2026
ER  -