# ATM-GAD: Adaptive Temporal Motif Graph Anomaly Detection for Financial Transaction Networks

## TL;DR

ATM-GAD is a novel adaptive graph neural network that detects financial fraud by analyzing temporal motifs and account-specific activity intervals, significantly improving detection accuracy over existing methods.

## Contribution

It introduces a new approach combining temporal motif extraction and adaptive time windows within a graph neural network for enhanced financial anomaly detection.

## Key findings

- Outperforms seven baseline methods on real-world datasets
- Effectively captures complex multi-step fraud schemes
- Identifies fraud patterns missed by previous models

## Abstract

Financial fraud detection is essential to safeguard billions of dollars, yet the intertwined entities and fast-changing transaction behaviors in modern financial systems routinely defeat conventional machine learning models. Recent graph-based detectors make headway by representing transactions as networks, but they still overlook two fraud hallmarks rooted in time: (1) temporal motifs--recurring, telltale subgraphs that reveal suspicious money flows as they unfold--and (2) account-specific intervals of anomalous activity, when fraud surfaces only in short bursts unique to each entity. To exploit both signals, we introduce ATM-GAD, an adaptive graph neural network that leverages temporal motifs for financial anomaly detection. A Temporal Motif Extractor condenses each account's transaction history into the most informative motifs, preserving both topology and temporal patterns. These motifs are then analyzed by dual-attention blocks: IntraA reasons over interactions within a single motif, while InterA aggregates evidence across motifs to expose multi-step fraud schemes. In parallel, a differentiable Adaptive Time-Window Learner tailors the observation window for every node, allowing the model to focus precisely on the most revealing time slices. Experiments on four real-world datasets show that ATM-GAD consistently outperforms seven strong anomaly-detection baselines, uncovering fraud patterns missed by earlier methods.