RIFF: Inducing Rules for Fraud Detection from Decision Trees

TL;DR

This paper introduces RIFF, a rule induction algorithm that extracts simple, interpretable rules from decision trees for fraud detection, maintaining or improving performance while reducing complexity and false positives.

Contribution

RIFF is a novel rule induction method that distills low FPR rule sets directly from decision trees, enhancing interpretability and efficiency in fraud detection.

Findings

Induced rules maintain or improve original model performance.

Rules are simpler and more interpretable than hand-tuned rules.

RIFF outperforms existing rule induction algorithms in low FPR scenarios.

Abstract

Financial fraud is the cause of multi-billion dollar losses annually. Traditionally, fraud detection systems rely on rules due to their transparency and interpretability, key features in domains where decisions need to be explained. However, rule systems require significant input from domain experts to create and tune, an issue that rule induction algorithms attempt to mitigate by inferring rules directly from data. We explore the application of these algorithms to fraud detection, where rule systems are constrained to have a low false positive rate (FPR) or alert rate, by proposing RIFF, a rule induction algorithm that distills a low FPR rule set directly from decision trees. Our experiments show that the induced rules are often able to maintain or improve performance of the original models for low FPR tasks, while substantially reducing their complexity and outperforming rules hand-tuned by experts.