{
  "id": 12592,
  "url": "https://arxiv.org/abs/2607.19266v1",
  "title": "Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation",
  "summary": "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",
  "authors": "Rahil Sharma",
  "category": "research",
  "topics": "agents-autonomy,transparency,finance-investment",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-21T16:37:41.000Z",
  "fetched_at": "2026-07-22T05:10:49.469Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/12592",
  "original_url": "https://arxiv.org/abs/2607.19266v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}