RIFF: Inducing Rules for Fraud Detection from Decision Trees
This addresses the need for transparent and interpretable fraud detection systems in finance, reducing reliance on expert input, though it is incremental as it builds on existing rule induction methods.
The paper tackles the problem of automating rule creation for fraud detection by proposing RIFF, a rule induction algorithm that distills low false positive rate rule sets from decision trees, resulting in rules that maintain or improve model performance while reducing complexity and outperforming expert-tuned rules.
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.