JDS Journal of Data Science 1683-86021680-743X1680-743X School of Statistics, Renmin University of China JDS1047 10.6339/22-JDS1047 Data Science Reviews A Review on Graph Neural Network Methods in Financial Applications WangJianian1 ZhangSheng1 XiaoYanghuashawyh@fudan.edu.cn2∗ SongRuirsong@ncsu.edu1∗ Department of Statistics, North Carolina State University, Raleigh, United States School of Computer Science, Fudan University, Shanghai, China Corresponding author. Email: shawyh@fudan.edu.cn or rsong@ncsu.edu. 2022252022202111134 Supplementary Material

In the supplementary materials, we present materials that are not covered in the main text. The supplementary materials contain the summary table for each financial application, figures categorizing major GNN methodologies for each graph type and acronyms used in the text.

31120211042022 2022 The Author(s). Published by the School of Statistics and the Center for Applied Statistics, Renmin University of China.2022 Open access article under the CC BY license.

With multiple components and relations, financial data are often presented as graph data, since it could represent both the individual features and the complicated relations. Due to the complexity and volatility of the financial market, the graph constructed on the financial data is often heterogeneous or time-varying, which imposes challenges on modeling technology. Among the graph modeling technologies, graph neural network (GNN) models are able to handle the complex graph structure and achieve great performance and thus could be used to solve financial tasks. In this work, we provide a comprehensive review of GNN models in recent financial context. We first categorize the commonly-used financial graphs and summarize the feature processing step for each node. Then we summarize the GNN methodology for each graph type, application in each area, and propose some potential research areas.

 deep learning finance graph convolutional network graph representation learning References Araci D (2019). Finbert: Financial sentiment analysis with pre-trained language models. arXiv preprint: https://arxiv.org/abs/1908.10063. Cer D, Yang Y, Kong S, Hua N, Limtiaco N, John RS et al. (2018). Universal sentence encoder for english. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 169–174. Chen Y, Wei Z, Huang X (2018). Incorporating corporation relationship via graph convolutional neural networks for stock price prediction. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 1655–1658. Cheng D, Niu Z, Zhang Y (2020). Contagious chain risk rating for networked-guarantee loans. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2715–2723. Cheng D, Tu Y, Ma Z, Niu Z, Zhang L (2019). Risk assessment for networked-guarantee loans using high-order graph attention representation. In: Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, IJCAI-19, 5822–5828. International Joint Conferences on Artificial Intelligence Organization. Cheng D, Wang X, Zhang Y, Zhang L (2020). Risk guarantee prediction in networked-loans. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI-20 (C Bessiere, ed.), 4483–4489. International Joint Conferences on Artificial Intelligence Organization. Special Track on AI in FinTech. Cho K, van Merrienboer B, Gulcehre C, Bougares F, Schwenk H, Bengio Y (2014). Learning phrase representations using rnn encoder-decoder for statistical machine translation. In: Conference on Empirical Methods in Natural Language Processing (EMNLP 2014). Devlin J, Chang MW, Lee K, Toutanova K (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), 4171–4186. Association for Computational Linguistics, Minneapolis, Minnesota. Dou Y, Liu Z, Sun L, Deng Y, Peng H, Yu PS (2020). Enhancing graph neural network-based fraud detectors against camouflaged fraudsters. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 315–324. Feng F, He X, Wang X, Luo C, Liu Y, Chua TS (2019). Temporal relational ranking for stock prediction. ACM Transactions on Information Systems (TOIS), 37(2): 1–30. Gori M, Monfardini G, Scarselli F (2005). A new model for learning in graph domains. In: Proceedings. 2005 IEEE International Joint Conference on Neural Networks, 2005, volume 2, 729–734. IEEE. Harl M, Weinzierl S, Stierle M, Matzner M (2020). Explainable predictive business process monitoring using gated graph neural networks. Journal of Decision Systems, 1–16. Hochreiter S, Schmidhuber J (1997). Long short-term memory. Neural computation, 9(8): 1735–1780. Hu B, Zhang Z, Shi C, Zhou J, Li X, Qi Y (2019). Cash-out user detection based on attributed heterogeneous information network with a hierarchical attention mechanism. In: Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 946–953. Hu B, Zhang Z, Zhou J, Fang J, Jia Q, Fang Y, et al. (2020). Loan default analysis with multiplex graph learning. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 2525–2532. Huang J, Chai J, Cho S (2020). Deep learning in finance and banking: A literature review and classification. Frontiers of Business Research in China, 14: 1–24. Jiang J, Chen J, Gu T, Choo KKR, Liu C, Yu M, et al. (2019). Anomaly detection with graph convolutional networks for insider threat and fraud detection. In: MILCOM 2019-2019 IEEE Military Communications Conference (MILCOM), 109–114. IEEE. Jiang W (2021). Applications of deep learning in stock market prediction: Recent progress. Expert Systems with Applications, 115537. Kipf TN, Welling M (2017). Semi-supervised classification with graph convolutional networks. In: International Conference on Learning Representations (ICLR). Kudo W, Nishiguchi M, Toriumi F (2020). Gcnext: Graph convolutional network with expanded balance theory for fraudulent user detection. Social Network Analysis and Mining, 10(1): 1–12. Kurshan E, Shen H (2020). Graph computing for financial crime and fraud detection: Trends, challenges and outlook. International Journal of Semantic Computing, 14(04): 565–589. Lee JB, Rossi RA, Kim S, Ahmed NK, Koh E (2019). Attention models in graphs: A survey. ACM Transactions on Knowledge Discovery from Data (TKDD), 13(6): 1–25. Lee JW, Lee WK, Sohn SY (2021). Graph convolutional network-based credit default prediction utilizing three types of virtual distances among borrowers. Expert Systems with Applications, 168: 114411. Li A, Qin Z, Liu R, Yang Y, Li D (2019a). Spam review detection with graph convolutional networks. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2703–2711. Li C, Jia K, Shen D, Shi CJR, Yang H (2019b). Hierarchical representation learning for bipartite graphs. In: IJCAI, 2873–2879. Li W, Bao R, Harimoto K, Chen D, Xu J, Su Q (2020a). Modeling the stock relation with graph network for overnight stock movement prediction. In: no. CONF, 4541–4547. Li X, Liu S, Li Z, Han X, Shi C, Hooi B, et al. (2020b). Flowscope: Spotting money laundering based on graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, 4731–4738. Li X, Saúde J, Reddy P, Veloso M (2019c). Classifying and understanding financial data using graph neural network. In: AAAI Workshop on Knowledge Discovery from Unstructured Data in Financial Services 2020. Li Y, Zemel R, Brockschmidt M, Tarlow D (2016). Gated graph sequence neural networks. In: Proceedings of ICLR’16. Li Z, Shen X, Jiao Y, Pan X, Zou P, Meng X, et al. (2020c). Hierarchical bipartite graph neural networks: Towards large-scale e-commerce applications. In: 2020 IEEE 36th International Conference on Data Engineering (ICDE), 1677–1688. IEEE. Liang C, Liu Z, Liu B, Zhou J, Li X, Yang S, et al. (2019). Uncovering insurance fraud conspiracy with network learning. In: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, 1181–1184. Liang T, Zeng G, Zhong Q, Chi J, Feng J, Ao X, et al. (2021). Credit risk and limits forecasting in e-commerce consumer lending service via multi-view-aware mixture-of-experts nets. In: Proceedings of the 14th ACM International Conference on Web Search and Data Mining, 229–237. Liou YT, Chen CC, Tang TH, Huang HH, Chen HH (2021). Finsense: An assistant system for financial journalists and investors. In: Proceedings of the 14th International Conference on Web Search and Data Mining. Liu Z, Chen C, Li L, Zhou J, Li X, Song L, et al. (2019). Geniepath: Graph neural networks with adaptive receptive paths. In: Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, 4424–4431. Liu Z, Chen C, Yang X, Zhou J, Li X, Song L (2018). Heterogeneous graph neural networks for malicious account detection. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, 2077–2085. Lv L, Cheng J, Peng N, Fan M, Zhao D, Zhang J (2019). Auto-encoder based graph convolutional networks for online financial anti-fraud. In: 2019 IEEE Conference on Computational Intelligence for Financial Engineering & Economics (CIFEr), 1–6. IEEE. Ma X, Sha J, Wang D, Yu Y, Yang Q, Niu X (2018). Study on a prediction of p2p network loan default based on the machine learning lightgbm and xgboost algorithms according to different high dimensional data cleaning. Electronic Commerce Research and Applications, 31: 24–39. Matsunaga D, Suzumura T, Takahashi T (2019). Exploring graph neural networks for stock market predictions with rolling window analysis. arXiv preprint: https://arxiv.org/abs/1909.10660. Ozbayoglu AM, Gudelek MU, Sezer OB (2020). Deep learning for financial applications: A survey. Applied Soft Computing, 106384. Pareja A, Domeniconi G, Chen J, Ma T, Suzumura T, Kanezashi H, et al. (2020). Evolvegcn: Evolving graph convolutional networks for dynamic graphs. In: Proceedings of the AAAI Conference on Artificial Intelligence, volume 34, 5363–5370. Pennington J, Socher R, Manning CD (2014). Glove: Global vectors for word representation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 1532–1543. Rao SX, Zhang S, Han Z, Zhang Z, Min W, Cheng M, Shan Y, Zhao Y, Zhang C (2020). Suspicious massive registration detection via dynamic heterogeneous graph neural networks. arXiv preprint: https://arxiv.org/abs/2012.10831. Rao SX, Zhang S, Han Z, Zhang Z, Min W, Chen Z, et al. (2020). xfraud: Explainable fraud transaction detection on heterogeneous graphs. arXiv preprint: https://arxiv.org/abs/2011.12193. Sawhney R, Agarwal S, Wadhwa A, Shah R (2020a). Deep attentive learning for stock movement prediction from social media text and company correlations. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 8415–8426. Sawhney R, Khanna P, Aggarwal A, Jain T, Mathur P, Shah R (2020b). Voltage: Volatility forecasting via text-audio fusion with graph convolution networks for earnings calls. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 8001–8013. Turiel J, Aste T (2020). Peer-to-peer loan acceptance and default prediction with artificial intelligence. Royal Society Open Science, 7(6): 191649. Veličković P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y (2018). Graph attention networks. In: International Conference on Learning Representations. Vrandečić D, Krötzsch M (2014). Wikidata: A free collaborative knowledgebase. Communications of the ACM, 57(10): 78–85. Wang D, Lin J, Cui P, Jia Q, Wang Z, Fang Y, et al. (2019). A semi-supervised graph attentive network for financial fraud detection. In: 2019 IEEE International Conference on Data Mining (ICDM), 598–607. IEEE Computer Society. Weber M, Domeniconi G, Chen J, Weidele DKI, Bellei C, Robinson T, et al. (2019). Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics. arXiv preprint: https://arxiv.org/abs/1908.02591. Wu Z, Pan S, Chen F, Long G, Zhang C, Philip SY (2020). A comprehensive survey on graph neural networks. In: IEEE Transactions on Neural Networks and Learning Systems, 4–24. IEEE. Xu B, Shen H, Sun B, An R, Cao Q, Cheng X (2021). Towards consumer loan fraud detection: Graph neural networks with role-constrained conditional random field. In: Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 4537–4545. Xu K, Hu W, Leskovec J, Jegelka S (2018). How powerful are graph neural networks? arXiv preprint: https://arxiv.org/abs/1810.00826. Yang H (2019). Aligraph: A comprehensive graph neural network platform. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 3165–3166. Yang S, Zhang Z, Zhou J, Wang Y, Sun W, Zhong X, et al. (2020). Financial risk analysis for smes with graph-based supply chain mining. In: Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, 4661–4667. Yang Y, Wei Z, Chen Q, Wu L (2019). Using external knowledge for financial event prediction based on graph neural networks. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2161–2164. Ying R, Bourgeois D, You J, Zitnik M, Leskovec J (2019). GNN explainer: A tool for post-hoc explanation of graph neural networks. CoRR, arXiv preprint: https://arxiv.org/abs/abs/1903.03894. Ying X, Xu C, Gao J, Wang J, Li Z (2020). Time-aware graph relational attention network for stock recommendation. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management, 2281–2284. Zhang M, Chen Y (2018). Link prediction based on graph neural networks. Advances in Neural Information Processing Systems, 31. Zhang S, Tong H, Xu J, Maciejewski R (2019). Graph convolutional networks: a comprehensive review. Computational Social Networks, 6(1): 1–23. Zhang S, Yin H, Chen T, Hung QVN, Huang Z, Cui L (2020). Gcn-based user representation learning for unifying robust recommendation and fraudster detection. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 689–698. Zhao T, Deng C, Yu K, Jiang T, Wang D, Jiang M (2021). Gnn-based graph anomaly detection with graph anomaly loss. In: The Second International Workshop on Deep Learning on Graphs: Methods and Applications (DLG-KDD’20). Available at: https://deep-learning-graphs.bitbucket.io/dlg-kdd20/. Zhou J, Cui G, Hu S, Zhang Z, Yang C, Liu Z, et al. (2020). Graph neural networks: A review of methods and applications. AI Open, 1: 57–81. Zhu YN, Luo X, Li YF, Bu B, Zhou K, Zhang W, et al. (2020). Heterogeneous mini-graph neural network and its application to fraud invitation detection. In: 2020 IEEE International Conference on Data Mining (ICDM), 891–899. IEEE.