Yifan Duan, Guibin Zhang, Shilong Wang, Xiaojiang Peng, Wang Ziqi, Junyuan Mao, Hao Wu, Xinke Jiang, Kun Wang
{"title":"CaT-GNN:通过因果时序图神经网络加强信用卡欺诈检测","authors":"Yifan Duan, Guibin Zhang, Shilong Wang, Xiaojiang Peng, Wang Ziqi, Junyuan Mao, Hao Wu, Xinke Jiang, Kun Wang","doi":"arxiv-2402.14708","DOIUrl":null,"url":null,"abstract":"Credit card fraud poses a significant threat to the economy. While Graph\nNeural Network (GNN)-based fraud detection methods perform well, they often\noverlook the causal effect of a node's local structure on predictions. This\npaper introduces a novel method for credit card fraud detection, the\n\\textbf{\\underline{Ca}}usal \\textbf{\\underline{T}}emporal\n\\textbf{\\underline{G}}raph \\textbf{\\underline{N}}eural \\textbf{N}etwork\n(CaT-GNN), which leverages causal invariant learning to reveal inherent\ncorrelations within transaction data. By decomposing the problem into discovery\nand intervention phases, CaT-GNN identifies causal nodes within the transaction\ngraph and applies a causal mixup strategy to enhance the model's robustness and\ninterpretability. CaT-GNN consists of two key components: Causal-Inspector and\nCausal-Intervener. The Causal-Inspector utilizes attention weights in the\ntemporal attention mechanism to identify causal and environment nodes without\nintroducing additional parameters. Subsequently, the Causal-Intervener performs\na causal mixup enhancement on environment nodes based on the set of nodes.\nEvaluated on three datasets, including a private financial dataset and two\npublic datasets, CaT-GNN demonstrates superior performance over existing\nstate-of-the-art methods. Our findings highlight the potential of integrating\ncausal reasoning with graph neural networks to improve fraud detection\ncapabilities in financial transactions.","PeriodicalId":501139,"journal":{"name":"arXiv - QuantFin - Statistical Finance","volume":"41 1","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2024-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"CaT-GNN: Enhancing Credit Card Fraud Detection via Causal Temporal Graph Neural Networks\",\"authors\":\"Yifan Duan, Guibin Zhang, Shilong Wang, Xiaojiang Peng, Wang Ziqi, Junyuan Mao, Hao Wu, Xinke Jiang, Kun Wang\",\"doi\":\"arxiv-2402.14708\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Credit card fraud poses a significant threat to the economy. While Graph\\nNeural Network (GNN)-based fraud detection methods perform well, they often\\noverlook the causal effect of a node's local structure on predictions. This\\npaper introduces a novel method for credit card fraud detection, the\\n\\\\textbf{\\\\underline{Ca}}usal \\\\textbf{\\\\underline{T}}emporal\\n\\\\textbf{\\\\underline{G}}raph \\\\textbf{\\\\underline{N}}eural \\\\textbf{N}etwork\\n(CaT-GNN), which leverages causal invariant learning to reveal inherent\\ncorrelations within transaction data. By decomposing the problem into discovery\\nand intervention phases, CaT-GNN identifies causal nodes within the transaction\\ngraph and applies a causal mixup strategy to enhance the model's robustness and\\ninterpretability. CaT-GNN consists of two key components: Causal-Inspector and\\nCausal-Intervener. The Causal-Inspector utilizes attention weights in the\\ntemporal attention mechanism to identify causal and environment nodes without\\nintroducing additional parameters. Subsequently, the Causal-Intervener performs\\na causal mixup enhancement on environment nodes based on the set of nodes.\\nEvaluated on three datasets, including a private financial dataset and two\\npublic datasets, CaT-GNN demonstrates superior performance over existing\\nstate-of-the-art methods. Our findings highlight the potential of integrating\\ncausal reasoning with graph neural networks to improve fraud detection\\ncapabilities in financial transactions.\",\"PeriodicalId\":501139,\"journal\":{\"name\":\"arXiv - QuantFin - Statistical Finance\",\"volume\":\"41 1\",\"pages\":\"\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-02-22\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - QuantFin - Statistical Finance\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2402.14708\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - QuantFin - Statistical Finance","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2402.14708","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Credit card fraud poses a significant threat to the economy. While Graph
Neural Network (GNN)-based fraud detection methods perform well, they often
overlook the causal effect of a node's local structure on predictions. This
paper introduces a novel method for credit card fraud detection, the
\textbf{\underline{Ca}}usal \textbf{\underline{T}}emporal
\textbf{\underline{G}}raph \textbf{\underline{N}}eural \textbf{N}etwork
(CaT-GNN), which leverages causal invariant learning to reveal inherent
correlations within transaction data. By decomposing the problem into discovery
and intervention phases, CaT-GNN identifies causal nodes within the transaction
graph and applies a causal mixup strategy to enhance the model's robustness and
interpretability. CaT-GNN consists of two key components: Causal-Inspector and
Causal-Intervener. The Causal-Inspector utilizes attention weights in the
temporal attention mechanism to identify causal and environment nodes without
introducing additional parameters. Subsequently, the Causal-Intervener performs
a causal mixup enhancement on environment nodes based on the set of nodes.
Evaluated on three datasets, including a private financial dataset and two
public datasets, CaT-GNN demonstrates superior performance over existing
state-of-the-art methods. Our findings highlight the potential of integrating
causal reasoning with graph neural networks to improve fraud detection
capabilities in financial transactions.