Papers › RIFF: Inducing Rules for Fraud Detection from Decision Trees

RIFF: Inducing Rules for Fraud Detection from Decision Trees

23 Aug 2024arXiv:2408.12989archive 2025-07-28

João Lucas Martins, João Bravo, Ana Sofia Gomes, Carlos Soares, Pedro Bizarro

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.

PaperPDF

Code

No code repository is listed for this paper in the archive or in Syntology's graph.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Fraud Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Fraud Detection BAF – Base LightGBM Recall @ 1% FPR 25.2% #1 of 12 Archive leaderboard report
Fraud Detection BAF – Base FIGS Recall @ 1% FPR 21% #2 of 12 Archive leaderboard report
Fraud Detection BAF – Base CART+RIFF Recall @ 1% FPR 18.4% #3 of 12 Archive leaderboard report
Fraud Detection BAF – Base CART Recall @ 1% FPR 16% #4 of 12 Archive leaderboard report
Fraud Detection BAF – Base FIGS+RIFF Recall @ 1% FPR 15.8% #5 of 12 Archive leaderboard report
Fraud Detection BAF – Base FIGU+RIFF Recall @ 1% FPR 15.5% #6 of 12 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

SET

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections