Research Projects

Financial Fraud Detection

As defined by Black’s Law Dictionary, fraud refers to a knowing misrepresentation of the truth or concealment of a material fact to induce another to act to his or her detriment. The classification of financial fraud has not reached a consensus because the types of financial fraud are varied and mounting. We construct a financial fraud classification framework according to the major financial institution involved, as depicted in the following figure.

alt text 

We identify the key challenge in financial fraud detection as the imbalanced learning problem on graphs and provide several solutions for this problem, namely re-sampling based method PC-GNN, metric optimization method AO-GNN, re-weighting based method BLS. The details of these models can be found in the following references.

Reference

  1. Yang Liu, Xiang Ao, Zidi Qin, Jianfeng Chi, Jinghua Feng, Hao Yang and Qing He. "Pick and Choose: A GNN-based Imbalanced Learning Approach for Fraud Detection", In Proceedings of the Web Conference (WWW), 2021. [Paper] [Code] [Slides] [Talk] [ACM]

  2. Mengda Huang, Yang Liu, Xiang Ao, Kuan Li, Jianfeng Chi, Jinghua Feng, Yang Hao and Qing He. "AUC-oriented Graph Neural Network for Fraud Detection", In Proceedings of the ACM Web Conference (WWW), Pages 1311–1321, 2022. [Paper] [Slides] [ACM]

  3. Linfeng Dong, Yang Liu, Xiang Ao, Jianfeng Chi, Jinghua Feng, Yang Hao and Qing He. "Bi-Level Selection via Meta Gradient for Graph-based Fraud Detection", In Proceedings of the 27th International Conference on Database Systems for Advanced Applications (DASFAA), 2022. [Paper] [Slides] [Springer]

  4. Qiwei Zhong, Yang Liu, Xiang Ao, Binbin Hu, Jinghua Feng, Jiayu Tang and Qing He. "Financial Defaulter Detection on Online Credit Payment via Multi-view Attributed Heterogeneous Information Network", In Proceedings of the Web Conference (WWW), 2020. [Paper] [Slides] [Talk] [ACM]

  5. Xiaoqian Zhu, Xiang Ao, Zidi Qin, Yanpeng Chang, Yang Liu, Qing He, Jianping Li. "Intelligent Financial Fraud Detection Practices in Post-Pandemic Era". The Innovation, Volume 2, Issue 4, 28 November 2021, 100176. [Paper] [The Innovation] [ScienceDirect]