IJBTT

Unifying AI and Rule-based Models for Financial Fraud Detection
	© 2024 by IJCTT Journal
	Volume-72 Issue-12
	Year of Publication : 2024
	Authors : Munikrishnaiah Sundararamaiah, Sevinthi Kali Sankar Nagarajan, Krishnamurty Raju Mudunuru, Rajesh Remala
	DOI :  10.14445/22312803/IJCTT-V72I12P107

How to Cite?

Munikrishnaiah Sundararamaiah, Sevinthi Kali Sankar Nagarajan, Krishnamurty Raju Mudunuru, Rajesh Remala, "Unifying AI and Rule-based Models for Financial Fraud Detection," International Journal of Computer Trends and Technology, vol. 72, no. 12, pp. 61-68, 2024. Crossref, https://doi.org/10.14445/22312803/IJCTT-V72I12P107

Abstract
Financial fraud has become increasingly sophisticated, necessitating a blend of traditional and modern technologies to combat it effectively. This paper explores integrating rules-based systems with Artificial Intelligence (AI) models, especially machine learning techniques, to detect, prevent, and mitigate financial fraud. Through a comprehensive literature review, this study evaluates existing fraud detection techniques, compares their strengths and weaknesses, and proposes a hybrid approach that leverages historical rules and data-driven AI insights. Real-world use cases are analyzed to demonstrate how combining these approaches can result in more accurate fraud detection with fewer false positives. The findings offer strategic insights for organizations seeking to enhance banking, insurance, and financial fraud detection systems. Building a fraud prevention framework often exceeds creating a highly accurate machine learning (ML) model due to an ever-changing landscape and customer expectations. Oftentimes, it involves a complex ETL process with a decision science setup that combines a rules engine with an ML platform. The requirements for such a platform include scalability and isolation of multiple workspaces for cross regional teams built on open-source standards. By design, such an environment empowers data scientists, engineers and analysts to collaborate securely. We will first look at using a data Lakehouse architecture combined with Databricks’ enterprise platform, which supports the infrastructure needs of all downstream applications of a fraud prevention application. This paper will reference Databricks’ core components of Lakehouse called Delta Engine, a high-performance query engine designed for scalability and performance on big data workloads, and MLflow, a fully managed ML governance tool to track ML experiments and quickly productize them.

Keywords
Financial fraud detection, Rules-based models, AI/ML models, Lakehouse architecture, Real-time data processing, Anomaly detection, Data validation.

Reference

[1] Michael Armbrust et al., “Lakehouse: A New Generation of Open Platforms that Unify Data Warehouses and Data Lakes,” Proceedings of CIDR, vol. 8, 2021.
[Google Scholar]
[2] Alejandro Correa Bahnsen, Djamila Aouada, and Björn Ottersten, “Example-Dependent Cost-Sensitive Decision Trees,” Expert Systems with Applications, vol. 42, no. 19, pp. 6609-6619, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[3] Richard J. Bolton, and David J. Hand, “Statistical Fraud Detection: A Review,” Statistical Science, vol. 17, no. 3, pp. 235-255, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Fabrizio Carcillo et al., “Combining Unsupervised and Supervised Learning in Credit Card Fraud Detection,” Information Sciences, vol. 557, pp. 317-331, 2021.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Ghosh, and Reilly, “Credit Card Fraud Detection with a Neural-Network,” Proceedings of the 27th Annual Hawaii International Conference on System Sciences, Wailea, HI, USA, vol. 3, pp. 621-630, 1994.
[CrossRef] [Google Scholar] [Publisher Link]
[6] Michael Armbrust et al., “Delta Lake: High-Performance ACID Table Storage over Cloud Object Stores,” Proceedings of the VLDB Endowment, vol. 13, no. 12, pp. 3411-3424, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Yufeng Kou et al., “Survey of Fraud Detection Techniques,” IEEE International Conference on Networking, Sensing and Control, 2004, Taipei, Taiwan, vol. 2, pp. 749-754, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[8] E.W.T. Ngai et al., “The Application of Data Mining Techniques in Financial Fraud Detection: A Classification Framework and an Academic Review of Literature,” Decision Support Systems, vol. 50, no. 3, pp. 559-569, 2011.
[CrossRef] [Google Scholar] [Publisher Link]