# Detection, Attribution, Narration: An End-to-End Pipeline for Explainable Money Mule Identification

arXiv: https://arxiv.org/abs/2607.17586 · HTML: https://mlsanity.com/paper/2607.17586/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 27 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 5 of 5)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [GraphXAIN: Narratives to Explain Graph Neural Networks](https://mlsanity.com/paper/2411.02540/) (2024)
- [Efficient Fraud Detection Using Deep Boosting Decision Trees](https://mlsanity.com/paper/2302.05918/) (2023)
- [A three-Level Framework for LLM-Enhanced eXplainable AI: From technical explanations to natural language](https://mlsanity.com/paper/2506.05887/) (2025)

## Abstract (arXiv)

Money mule accounts are critical facilitators of financial fraud, yet detecting them at scale remains challenging due to the heterogeneous nature of transactional and behavioural data. We present an end-to-end pipeline for customer-level mule detection comprising three stages: (1) a LightGBM classifier trained on 280 engineered features spanning transaction patterns, account demographics, network topology, and temporal behaviour; (2) a TreeSHAP attribution layer that decomposes each prediction into feature contributions; and (3) a large language model (LLM) module that converts SHAP attributions into analyst-facing natural-language narratives. We evaluate across three open-weight LLM families and assess explanation quality through analyst feedback. In a live production deployment, the system achieves a yield rate of 89%, up from 61% under the incumbent rule-based system, with monthly alert volume expanding from 211 to 302, reflecting broader true-positive coverage rather than increased noise. This corresponds to a 60% incremental adverse detection beyond existing review workflows, substantially outperforming the rule-based approach. Qualitative feedback from analysts indicates that LLM-generated narratives reduce cognitive load during alert triage. We further discuss implications of deploying LLM-augmented explainability in regulated financial environments.