# Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation

arXiv: https://arxiv.org/abs/2607.19266 · HTML: https://mlsanity.com/paper/2607.19266/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 28 references that are in the map.
- First posted on arXiv 21 Jul 2026.

## Builds on (most cited first, 15 of 15)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [Graph Neural Networks for Financial Fraud Detection: A Review](https://mlsanity.com/paper/2411.05815/) (2024)
- [A Label-Free Heterophily-Guided Approach for Unsupervised Graph Fraud Detection](https://mlsanity.com/paper/2502.13308/) (2025)
- [Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects](https://mlsanity.com/paper/2507.21407/) (2025)
- [SEFraud: Graph-based Self-Explainable Fraud Detection via Interpretative Mask Learning](https://mlsanity.com/paper/2406.11389/) (2024)
- [Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time](https://mlsanity.com/paper/2511.07023/) (2025)
- [Can LLMs Find Fraudsters? Multi-level LLM Enhanced Graph Fraud Detection](https://mlsanity.com/paper/2507.11997/) (2025)
- [A Comparison Study of Credit Card Fraud Detection: Supervised versus Unsupervised](https://mlsanity.com/paper/1904.10604/) (2019)
- [Autonomous Chain-of-Thought Distillation for Graph-Based Fraud Detection](https://mlsanity.com/paper/2601.22949/) (2026)
- [Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection](https://mlsanity.com/paper/2605.28524/) (2026)
- [SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection](https://mlsanity.com/paper/2606.08146/) (2026)

## Abstract (arXiv)

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 signal improves Average Precision on the full test set. Both, however, rank fraud better within the subset of cases receiving intermediate baseline scores. In a controlled experiment with injected multi-account fraud rings, engineered structural features recover all injected test transactions, while the tabular baseline misses roughly a quarter of them. The investigation agent underperforms direct thresholding of the classifier it relies on, reaching 65.0% accuracy against 71.7% on a balanced 60-case sample, despite having access to model explanations, graph context, and retrieved reference cases. Of the eight decisions the agent changed, six replaced correct classifier outputs with errors, and it produced a coherent written rationale in each case. An exploratory disagreement-based escalation rule flagged two of these agent errors for human review without flagging any correct decision. We conclude that each component of a layered fraud system contributes only under specific conditions, and that a plausible rationale from an investigation agent is not evidence of a better decision.