Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation
Fraud detection systems must scale with rising transaction volume while remaining explainable and reviewable. We study a layered pipeline on the PaySim dataset that combines a gradient-boosted classifier, graph-derived structural features, an autoencoder-based anomaly signal, TreeSHAP explanations, and a bounded LLM investigation agent applied to cases the classifier scores uncertainly. Before any model comparison, we identify and remove a simulator-specific balance shortcut that would otherwise inflate baseline performance. After this correction, neither the graph features nor the anomaly sig
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 49%Building an AI loan document intelligence platform — shipped fraud detection, hybrid search, and 3-tier email fallback this week[P] →
- FuzzyOverlapping authors or contributors · 62%deepfakes/faceswap →
“Shared author/contributor keys: sharma”
- FuzzyOverlapping authors or contributors · 62%ultralytics/yolov5 →
“Shared author/contributor keys: sharma”
- FuzzySimilar title/name (fuzzy) · 59%tirth8205/code-review-graph →
“Fuzzy title match (0.73): “Toward Auditable Fraud Detection: Combining Graph Features, ” ≈ “tirth8205/code-review-graph””
- FuzzySimilar title/name (fuzzy) · 59%Fosowl/agenticSeek →
“Fuzzy title match (0.73): “Toward Auditable Fraud Detection: Combining Graph Features, ” ≈ “Fosowl/agenticSeek””
- LinkedLinked via arxiv author · 85%Rahil Sharma →
“Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation”