Abstract
Recent research on transfer learning reveals that adversarial domain adaptation effectively narrows the difference between the source and the target domain distributions, and realizes better transfer of the source domain knowledge. However, how to overcome the intra/inter-domain imbalance problems in domain adaptation, e.g. observed in cross-domain credit risk forecasting, is under-explored. The intra-domain imbalance problem results from the extremely limited throngs, e.g., defaulters, in both source and target domain. Meanwhile, the disparity in sample size across different domains leads to suboptimal transferability, which is known as the inter-domain imbalance problem. In this paper, we propose an unsupervised purifier training based transfer learning approach named ADAPTĀ (Adversarial Domain Adaptation with Purifier Training) to resolve the intra/inter-domain imbalance problems in domain adaptation. We also extend our ADAPT method to the multi-source domain adaptation via weighted source integration. We investigate the effectiveness of our method on a real-world industrial dataset on cross-domain credit risk forecasting containing 1.33 million users. Experimental results exhibit that the proposed method significantly outperforms the state-of-the-art methods. Visualization of the results further witnesses the interpretability of our method.
G. Zeng, J. ChiāContributed equally.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Altman, E.I.: Financial ratios, discriminant analysis and the prediction of corporate bankruptcy. J. Financ. 23(4), 589ā609 (1968)
Chi, J., et al.: Learning to undersampling for class imbalanced credit risk forecasting. In: ICDM, pp. 72ā81 (2020)
Gretton, A., Borgwardt, K.M., Rasch, M.J., Schƶlkopf, B., Smola, A.: A kernel two-sample test. J. Mach. Learn. Res. 13(1), 723ā773 (2012)
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, vol. 33, no. 01, pp. 946ā953 (2019)
Johnson, J.M., Khoshgoftaar, T.M.: Survey on deep learning with class imbalance. J. Big Data 6(1), 1ā54 (2019). https://doi.org/10.1186/s40537-019-0192-5
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2015)
Kingma, D.P., Welling, M.: Auto-encoding variational Bayes. In: ICLR (2013)
Liang, T., et al.: Credit risk and limits forecasting in e-commerce consumer lending service via multi-view-aware mixture-of-experts nets. In: WSDM, pp. 229ā237 (2021)
Lin, W., et al.: Online credit payment fraud detection via structure-aware hierarchical recurrent neural network. In: IJCAI (2021)
Liu, C., Sun, L., Ao, X., Feng, J., He, Q., Yang, H.: Intention-aware heterogeneous graph attention networks for fraud transactions detection. In: KDD, pp. 3280ā3288 (2021)
Liu, C., et al.: Fraud transactions detection via behavior tree with local intention calibration. In: KDD, pp. 3035ā3043 (2020)
Liu, Y., et al.: Pick and choose: a GNN-based imbalanced learning approach for fraud detection. In: WWW, pp. 3168ā3177 (2021)
Liu, Y., Ao, X., Zhong, Q., Feng, J., Tang, J., He, Q.: Alike and unlike: resolving class imbalance problem in financial credit risk assessment. In: CIKM, pp. 2125ā2128 (2020)
Malekipirbazari, M., Aksakalli, V.: Risk assessment in social lending via random forests. Expert Syst. Appl. 42(10), 4621ā4631 (2015)
Shen, J., Qu, Y., Zhang, W., Yu, Y.: Wasserstein distance guided representation learning for domain adaptation. In: AAAI (2018)
Siddiqui, M.A., Fern, A., Dietterich, T.G., Wright, R., Theriault, A., Archer, D.W.: Feedback-guided anomaly discovery via online optimization. In: KDD, pp. 2200ā2209 (2018)
Tzeng, E., Hoffman, J., Saenko, K., Darrell, T.: Adversarial discriminative domain adaptation. In: CVPR, pp. 7167ā7176 (2017)
Wang, C., Yu, Z., Zheng, H., Wang, N., Zheng, B.: CGAN-plankton: towards large-scale imbalanced class generation and fine-grained classification. In: ICIP, pp. 855ā859 (2017)
Wang, D., et al.: A semi-supervised graph attentive network for financial fraud detection. In: ICDM, pp. 598ā607 (2019)
Wang, S., Zhang, L.: Self-adaptive re-weighted adversarial domain adaptation. In: IJCAI (2020)
Xu, M., et al.: Adversarial domain adaptation with domain mixup. In: AAAI, vol. 34, no. 4, pp. 6502ā6509 (2020)
Zhao, H., Zhang, S., Wu, G., Moura, J.M., Costeira, J.P., Gordon, G.J.: Adversarial multiple source domain adaptation. In: NeurIPS (2018)
Zhao, S., et al.: Multi-source distilling domain adaptation. In: AAAI, vol. 34, no. 7, pp. 12975ā12983 (2020)
Zheng, W., Zhao, H.: Cost-sensitive hierarchical classification for imbalance classes. Appl. Intell. 50(8), 2328ā2338 (2020). https://doi.org/10.1007/s10489-019-01624-z
Zhong, Q., et al.: Financial defaulter detection on online credit payment via multi-view attributed heterogeneous information network. In: WWW, pp. 785ā795 (2020)
Zhu, Y., et al.: Modeling usersā behavior sequences with hierarchical explainable network for cross-domain fraud detection. In: WWW, pp. 928ā938 (2020)
Acknowledgment
The research work supported by Alibaba Group through Alibaba Innovative Research Program and the National Natural Science Foundation of China under Grant (No.61976204, 92046003, U1811461). Xiang Ao is also supported by the Project of Youth Innovation Promotion Association CAS, Beijing Nova Program Z201100006820062.
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
Ā© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Zeng, G., Chi, J., Ma, R., Feng, J., Ao, X., Yang, H. (2022). ADAPT: Adversarial Domain Adaptation with Purifier Training for Cross-Domain Credit Risk Forecasting. In: Bhattacharya, A., et al. Database Systems for Advanced Applications. DASFAA 2022. Lecture Notes in Computer Science, vol 13245. Springer, Cham. https://doi.org/10.1007/978-3-031-00123-9_29
Download citation
DOI: https://doi.org/10.1007/978-3-031-00123-9_29
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-00122-2
Online ISBN: 978-3-031-00123-9
eBook Packages: Computer ScienceComputer Science (R0)