GraphFAS improves fraud detection with better graph features and selection
GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks
Machine LearningArtificial IntelligenceDistributed, Parallel, and Cluster Computing
Summary
Detecting fraud in large transaction networks is hard because it usually needs experts to design features, and many advanced methods are hard to explain or use in practice. The authors created GraphFAS, a system that automatically finds useful features from graph data without complex training steps. It builds clear and understandable features from graph connections and uses a smart process to pick the best ones across many machines. This method works well in a real-world setting, such as Alipay, improving efficiency and competitive performance compared to existing methods.
graph feature generationfeature selectionBoruta algorithmgraph neural networksfraud detectionmulti-hop subgraphdistributed systemsTreeSHAP explanationstransaction networksinterpretable models
Authors
Yice Luo, Yun Zhu, Xi Chen, Yongchao Liu, Xintan Zeng, Chengying Huan, Kai Zhang, Jinrui Zhang, Juelu Zhang, Jiajun Zheng
Abstract
Industrial fraud detection often relies on costly expert-crafted features that overlook graph-structured relational signals, while GNNs often do not meet the interpretability and deployment requirements of financial risk control. We propose GraphFAS (Graph Feature Automated Selection), a distributed feature selection procedure based on Boruta that bridges this gap through: (1) a non-parametric graph feature generation module that constructs explicit, interpretable structural features via multi-hop subgraph extraction and multi-scale aggregation without learned parameters; and (2) an automated distributed feature selection algorithm extending Boruta with median-based aggregation across partitions to robustly identify informative features at scale with minimal domain expertise. Compared with end-to-end GNN pipelines, GraphFAS decouples feature aggregation from model training, enabling direct integration with tabular models and direct compatibility with TreeSHAPbased explanations. Deployed in Alipay, GraphFAS delivers orderof-magnitude improvements in engineering efficiency while showing strong performance against expert-driven and graph-learning baselines on large-scale graphs.