Papers › Network analytics for insurance fraud detection: a critical case study
Network analytics for insurance fraud detection: a critical case study
Bruno Deprez, Félix Vandervorst, Wouter Verbeke, Bart Baesens, Tim Verdonck
There has been an increasing interest in fraud detection methods, driven by new regulations and by the financial losses linked to fraud. One of the state-of-the-art methods to fight fraud is network analytics. Network analytics leverages the interactions between different entities to detect complex patterns that are indicative of fraud. However, network analytics has only recently been applied to fraud detection in the actuarial literature. Although it shows much potential, many network methods are not yet applied. This paper extends the literature in two main ways. First, we review and apply multiple methods in the context of insurance fraud and assess their predictive power against each other. Second, we analyse the added value of network features over intrinsic features to detect fraud. We conclude that (1) complex methods do not necessarily outperform basic network features, and that (2) network analytics helps to detect different fraud patterns, compared to models trained on claim-specific features alone.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Fraud Detection | Healthcare Provider Fraud Detection Analysis | BiRank | AUC | 0.786 | #1 of 3 | Archive leaderboard | report |
| Fraud Detection | Healthcare Provider Fraud Detection Analysis | BiRank | AUPRC | 0.175 | #1 of 3 | Archive leaderboard | report |
| Fraud Detection | Healthcare Provider Fraud Detection Analysis | GraphSAGE | AUC | 0.668 | #2 of 3 | Archive leaderboard | report |
| Fraud Detection | Healthcare Provider Fraud Detection Analysis | GraphSAGE | AUPRC | 0.201 | #2 of 3 | Archive leaderboard | report |
| Fraud Detection | Healthcare Provider Fraud Detection Analysis | metapath2vec | AUC | 0.513 | #3 of 3 | Archive leaderboard | report |
| Fraud Detection | Healthcare Provider Fraud Detection Analysis | metapath2vec | AUPRC | 0.054 | #3 of 3 | 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
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