Citation :

Sumit Asthana, "A Theoretical Framework for Hybrid Rule-Based and Machine-Learning Fraud Detection," International Journal of Computer Trends and Technology (IJCTT), vol. 74, no. 3, pp. 7-13, 2026. Crossref, https://doi.org/10.14445/22312803/IJCTT-V74I3P102

Abstract

This paper introduces a practical approach to modern fraud detection by combining rule-based systems with machine learning models. Traditional systems often work in isolation, rely heavily on static rules, and struggle to identify emerging or complex fraud patterns. To address these challenges, we propose a hybrid framework that blends the clear logic of rules with the adaptive strengths of machine learning. The solution includes a two-layer model: a first layer using supervised techniques to predict known fraud types, and a second layer using unsupervised methods to validate for errors, both missed frauds and false alerts. A shared feature store ensures consistent data usage across training and real-time prediction, while explainability tools help analysts understand model decisions.

Keywords

Fraud Detection, Hybrid Models, Machine Learning, Rule-Based Systems, Anomaly Detection, Explainable AI.

References

[1] Vishnu Vardhan et al., “Anomaly Detection in Credit Card Transactions using Autoencoders,” International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, pp. 128-133, 2024.
[CrossRef] [Google Scholar] [Publisher Link]

[2] Fabrizio Carcillo et al., “Combining Unsupervised and Supervised Learning in Credit Card Fraud Detection,” Information Sciences, vol. 557, pp. 317-331, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Sergei Krutikov et al., “Challenging Gradient Boosted Decision Trees with Tabular Transformers for Fraud Detection at Booking.com,” arXiv Preprint, pp. 1-9, 2018.
[CrossRef] [Google Scholar] [Publisher Link] 

[4] V. Venu Madhav, and K. Aruna Kumari, “Analysis of Credit Card Fraud Data using PCA,” IOSR Journal of Engineering, vol. 10, no. 1, pp. 10-14, 2020.
[Publisher Link] 

[5] Ela Guven, “A Comparative Analysis of Autoencoders for Credit Card Fraud Detection,” Tilburg University Repository, 2024.

         [Google Scholar] [Publisher Link] 

[6] Yisong Chen et al., “Year‑Over‑Year Developments in Financial Fraud Detection via Deep Learning: A Systematic Literature Review,” arXiv Preprint, pp. 1-21, 2025.

        [CrossRef] [Google Scholar] [Publisher Link]