AI-Powered Dynamic Risk Scoring for E-commerce Transactions

Authors

  • Surendra Lakkaraju University of Houston, USA Author

DOI:

https://doi.org/10.32628/CSEIT251112363

Keywords:

Dynamic Risk Assessment, Fraud Detection, Machine Learning, Reinforcement Learning, Bayesian Networks

Abstract

This article presents a comprehensive framework for dynamic risk assessment in e-commerce fraud detection using advanced machine learning techniques. The article introduces an innovative approach combining reinforcement learning, Bayesian networks, and real-time processing architectures to address the challenges of modern fraud detection. The implementation demonstrates significant improvements in fraud detection accuracy, reduction in false positives, and enhanced customer experience through adaptive risk scoring mechanisms. The system incorporates sophisticated feature engineering, network-aware processing, and continuous model optimization to maintain performance across transaction patterns and network conditions. The article provides detailed analysis of system architecture, performance metrics, and implementation challenges, offering solutions for data imbalance, real-time processing, and model drift management in large-scale e-commerce environments.

Downloads

Download data is not yet available.

References

GetFocal AI Research Institute, "Ecommerce Fraud: Detection, Prevention, Red Flags, & Future Trends," 2024. Available: https://www.getfocal.ai/blog/ecommerce-fraud-detection-and-prevention-best-practices

Sana Commerce Research Group, "10 key e-commerce business risks and how to solve them," 2022. Available: https://www.sana-commerce.com/blog/solve-ecommerce-business-risks/

Shouzhen Zeng, et al., "Risk evaluation of livestream e-commerce platforms based on expert trust networks and CODAS," 2025. Available: https://www.sciencedirect.com/science/article/abs/pii/S0957417424022759

Pushkar Mehendale, "Scalable Architecture for Machine Learning Applications," 2024. Available: https://jsaer.com/download/vol-11-iss-8-2024/JSAER2024-11-8-111-117.pdf

Junwei Xie, "Application Study on the Reinforcement Learning Strategies in the Network Awareness Risk Perception and Prevention," International Journal of Computational Intelligence Systems, Volume 17, article number 112, (2024), 07 May 2024. [Online]. Available: https://link.springer.com/article/10.1007/s44196-024-00492-x

Jacob Raymond et al., "Financial Fraud Detection Feature Engineering Techniques for Enhanced Security Systems," ResearchGate, December 2024. [Online]. Available: https://www.researchgate.net/publication/386986127_Financial_Fraud_Detection_Feature_Engineering_Techniques_for_Enhanced

Abbassi Hanae et al., "End-to-End Real-time Architecture for Fraud Detection in Online Digital Transactions," (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 14, No. 6, 2023. [Online]. Available: https://thesai.org/Downloads/Volume14No6/Paper_80-End-to-End%20Real-time%20Architecture%20for%20Fraud%20Detection.pdf

Jaakko Hollmén, "Probabilistic Approaches to Fraud Detection," Helsinki University of Technology, 1999. [Online]. Available: https://users.aalto.fi/~jhollmen/pubs/publications/Hollmen99b.pdf

Surendranadha Reddy Byrapu Reddy et al., "Effective fraud detection in e-commerce: Leveraging machine learning and big data analytics," Measurement: Sensors, Volume 33, June 2024, 101138. [Online]. Available: https://www.sciencedirect.com/science/article/pii/S2665917424001144

Oluwabusayo Bello et al., "Analysing the Impact of Advanced Analytics on Fraud Detection: A Machine Learning Perspective," ResearchGate, January 2023. [Online]. Available: https://www.researchgate.net/publication/381548526_Analysing_the_Impact_of_Advanced_Analytics_on_Fraud_Detection_A_Machine_Learning_Perspective

Zainab Saad Rubaidi et al., "Fraud Detection Using Large-scale Imbalance Dataset: A Comprehensive Analysis," International Journal on Artificial Intelligence Tools, Vol. 31, No. 8 (2022). [Online]. Available: https://www.worldscientific.com/doi/pdf/10.1142/S0218213022500373#

Materialize, "A Reference Architecture for Real-Time Fraud Detection," 2024. [Online]. Available: https://landing.materialize.com/hubfs/whitepapers/2024/a_reference_architetcture_for_real-time_fraud_detection.pdf

Downloads

Published

25-02-2025

Issue

Section

Research Articles

How to Cite

AI-Powered Dynamic Risk Scoring for E-commerce Transactions. (2025). International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 11(1), 3515-3526. https://doi.org/10.32628/CSEIT251112363