Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.12989 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914921447424000 |
|---|---|
| author | Martins, João Lucas Bravo, João Gomes, Ana Sofia Soares, Carlos Bizarro, Pedro |
| author_facet | Martins, João Lucas Bravo, João Gomes, Ana Sofia Soares, Carlos Bizarro, Pedro |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12989 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | RIFF: Inducing Rules for Fraud Detection from Decision Trees Martins, João Lucas Bravo, João Gomes, Ana Sofia Soares, Carlos Bizarro, Pedro Machine Learning Artificial Intelligence 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. |
| title | RIFF: Inducing Rules for Fraud Detection from Decision Trees |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2408.12989 |