Abstract
Anomaly detection in the financial domain aims to detect abnormal transactions such as fraudulent transactions that can lead to loss of revenues to financial institutions. Existing solutions utilize solely transaction attributes as feature representations without the consideration of direct/indirect interactions between users and transactions, leading to limited accuracy. We formulate anomaly detection in financial transactions as the problem of edge classification in an edge-attributed multigraph, where each transaction is regarded as an edge, and each user is represented by a node. Then, we propose an effective solution \(\texttt{DoubleFA}\), which contains two novel schemes: proximal feature aggregation and anomaly feature aggregation. The former is to aggregate features from neighborhoods into edges based on top-k Personalized PageRank (PPR). In anomaly feature aggregation, we employ a predict-and-aggregate strategy to accurately preserve anomaly information, thereby alleviating the over-smoothing issue incurred by proximal feature aggregation. Our experiments comparing \(\texttt{DoubleFA}\) against 10 baselines on real transaction datasets from PayPal demonstrate that \(\texttt{DoubleFA}\) consistently outperforms all baselines in terms of anomaly detection accuracy. In particular, on the full PayPal dataset with 160 million users and 470 million transactions, our method achieves a significant improvement of at least 23% in F1 score compared to the best competitors.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Brand, M.: Fast low-rank modifications of the thin singular value decomposition. Linear Algebra Appl. 415(1), 20–30 (2006)
Chen, T., Guestrin, C.: XGBoost: a scalable tree boosting system. In: KDD, vol. 13–17-August, pp. 785–794 (2016)
Dai, Q., Shen, X., Zhang, L., Li, Q., Wang, D.: Adversarial training methods for network embedding. In: WWW, pp. 329–339 (2019)
Goldstein, M., Dengel, A.: Histogram-based outlier score (hbos): a fast unsupervised anomaly detection algorithm. KI(1), 59–63 (2012)
Goyal, P., Chhetri, S.R., Canedo, A.: dyngraph2vec: Capturing network dynamics using dynamic graph representation learning. Knowl.-Based Syst. 187, 104816 (2020)
Grover, A., Leskovec, J.: Node2vec: scalable feature learning for networks. In: KDD, pp. 855–864 (2016)
Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: NeurIPS, pp. 1025–1035, June 2017
Hu, B., Zhang, Z., Shi, C., Zhou, J., Li, X., Qi, Y.: Cash-out user detection based on attributed heterogeneous information network with a hierarchical attention mechanism. In: AAAI, pp. 946–953 (2019)
Jeh, G., Widom, J.: Scaling personalized web search. In: WWW, pp. 271–279 (2003)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. In: ICLR (2017)
Klicpera, J., Bojchevski, A., Günnemann, S.: Predict then propagate: graph neural networks meet personalized PageRank. In: ICLR, October 2019
Liu, F.T., Ting, K.M., Zhou, Z.H.: Isolation forest. In: ICDM, pp. 413–422 (2008)
Liu, Y., et al.: Pick and choose: a GNN-based imbalanced learning approach for fraud detection. In: WWW, pp. 3168–3177. WWW 2021 (2021)
Liu, Z., Dou, Y., Yu, P.S., Deng, Y., Peng, H., Peng, H.: Alleviating the inconsistency problem of applying graph neural network to fraud detection. In: SIGIR, pp. 1569–1572 (2020)
PayPal Holdings Inc: Annual Report Pursuant to Section 13 or 15(d) of The Securities Exchange Act of 1934. https://www.sec.gov/Archives/edgar/data/1633917/000163391721000018/pypl-20201231.html(2020)
Perozzi, B., Al-Rfou, R., Skiena, S.: DeepWalk: Online learning of social representations. In: KDD, pp. 701–710 (2014)
Qiu, J., et al.: Netsmf: large-scale network embedding as sparse matrix factorization. In: WWW, pp. 1509–1520 (2019)
Ramaswamy, S., Rastogi, R., Shim, K.: Efficient algorithms for mining outliers from large data sets. SIGMOD Record 29(2), 427–438 (2000)
Ravisankar, P., Ravi, V., Raghava Rao, G., Bose, I.: Detection of financial statement fraud and feature selection using data mining techniques. In: DSS, pp. 491–500 (2011)
Swersky, L., Marques, H.O., Jörg, S., Campello, R.J., Zimek, A.: On the evaluation of outlier detection and one-class classification methods. In: DSAA, pp. 1–10 (2016)
Veličković, P., Casanova, A., Liò, P., Cucurull, G., Romero, A., Bengio, Y.: Graph attention networks. Technical Report (2018)
Wang, C., Wang, C., Wang, Z., Ye, X., Yu, P.S.: Edge2vec: edge-based social network embedding. TKDD 14(4), 1–24 (2020)
Wang, D., et al.: A semi-supervised graph attentive network for financial fraud detection. In: ICDM, pp. 598–607 (2019)
Wang, J., Wen, R., Wu, C., Huang, Y., Xiong, J.: FDGars: fraudster detection via graph convolutional networks in online app review system. In: WWW, pp. 310–316 (2019)
Wang, S., Yang, R., Xiao, X., Wei, Z., Yang, Y.: FORA: simple and effective approximate single-source personalized PageRank. In: KDD, pp. 505–514 (2017)
Weber, M., et al.: Anti-money laundering in bitcoin: experimenting with graph convolutional networks for financial forensics. arXiv (2019)
Wu, F., Zhang, T., de Souza, A.H., Fifty, C., Yu, T., Weinberger, K.Q.: Simplifying graph convolutional networks. In: arXiv (2019)
Yun, S., Jeong, M., Kim, R., Kang, J., Kim, H.J.: Graph transformer networks. In: Wallach, H., Larochelle, H., Beygelzimer, A., d Alché-Buc, F., Fox, E., Garnett, R. (eds.) NeurIPS. vol. 32 (2019)
Zhang, Y., Fan, Y., Ye, Y., Zhao, L., Shi, C.: Key player identification in underground forums over attributed heterogeneous information network embedding framework. In: CIKM, pp. 549–558, November 2019
Zhang, Z., Cui, P., Li, H., Wang, X., Zhu, W.: Billion-scale network embedding with iterative random projection. In: ICDM, pp. 787–796 (2018)
Zhang, Z., Pei, J., Cui, P., Yao, X., Wang, X., Zhu, W.: Arbitrary-order proximity preserved network embedding. In: KDD, pp. 2778–2786 (2018)
Zhong, Q., et al.: Financial defaulter detection on online credit payment via multi-view attributed heterogeneous information network. In: WWW, pp. 785–795, April 2020
Zhu, J., Yan, Y., Zhao, L., Heimann, M., Akoglu, L., Koutra, D.: Beyond homophily in graph neural networks: Current limitations and effective designs. In: NeurIPS, vol. 2020-December (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Wang, H., Yang, R., Shi, J. (2023). Anomaly Detection in Financial Transactions Via Graph-Based Feature Aggregations. In: Wrembel, R., Gamper, J., Kotsis, G., Tjoa, A.M., Khalil, I. (eds) Big Data Analytics and Knowledge Discovery. DaWaK 2023. Lecture Notes in Computer Science, vol 14148. Springer, Cham. https://doi.org/10.1007/978-3-031-39831-5_6
Download citation
DOI: https://doi.org/10.1007/978-3-031-39831-5_6
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-39830-8
Online ISBN: 978-3-031-39831-5
eBook Packages: Computer ScienceComputer Science (R0)