IDEAS home Printed from https://ideas.repec.org/p/arx/papers/2308.03704.html
   My bibliography  Save this paper

DeRisk: An Effective Deep Learning Framework for Credit Risk Prediction over Real-World Financial Data

Author

Listed:
  • Yancheng Liang
  • Jiajie Zhang
  • Hui Li
  • Xiaochen Liu
  • Yi Hu
  • Yong Wu
  • Jinyao Zhang
  • Yongyan Liu
  • Yi Wu

Abstract

Despite the tremendous advances achieved over the past years by deep learning techniques, the latest risk prediction models for industrial applications still rely on highly handtuned stage-wised statistical learning tools, such as gradient boosting and random forest methods. Different from images or languages, real-world financial data are high-dimensional, sparse, noisy and extremely imbalanced, which makes deep neural network models particularly challenging to train and fragile in practice. In this work, we propose DeRisk, an effective deep learning risk prediction framework for credit risk prediction on real-world financial data. DeRisk is the first deep risk prediction model that outperforms statistical learning approaches deployed in our company's production system. We also perform extensive ablation studies on our method to present the most critical factors for the empirical success of DeRisk.

Suggested Citation

  • Yancheng Liang & Jiajie Zhang & Hui Li & Xiaochen Liu & Yi Hu & Yong Wu & Jinyao Zhang & Yongyan Liu & Yi Wu, 2023. "DeRisk: An Effective Deep Learning Framework for Credit Risk Prediction over Real-World Financial Data," Papers 2308.03704, arXiv.org.
  • Handle: RePEc:arx:papers:2308.03704
    as

    Download full text from publisher

    File URL: http://arxiv.org/pdf/2308.03704
    File Function: Latest version
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Guo, Yanhong & Zhou, Wenjun & Luo, Chunyu & Liu, Chuanren & Xiong, Hui, 2016. "Instance-based credit risk assessment for investment decisions in P2P lending," European Journal of Operational Research, Elsevier, vol. 249(2), pages 417-426.
    2. Jianping Li & Xiaoqian Zhu & Cheng-Few Lee & Dengsheng Wu & Jichuang Feng & Yong Shi, 2015. "On the aggregation of credit, market and operational risks," Review of Quantitative Finance and Accounting, Springer, vol. 44(1), pages 161-189, January.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Gourieroux, Christian & Lu, Yang, 2019. "Least impulse response estimator for stress test exercises," Journal of Banking & Finance, Elsevier, vol. 103(C), pages 62-77.
    2. Yeh, Jen-Yin & Chiu, Hsin-Yu & Huang, Jhih-Huei, 2024. "Predicting failure of P2P lending platforms through machine learning: The case in China," Finance Research Letters, Elsevier, vol. 59(C).
    3. Štefan Lyócsa & Petra Vašaničová & Branka Hadji Misheva & Marko Dávid Vateha, 2022. "Default or profit scoring credit systems? Evidence from European and US peer-to-peer lending markets," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 8(1), pages 1-21, December.
    4. Isaac Appiah-Otoo & Na Song, 2021. "The Impact of Fintech on Poverty Reduction: Evidence from China," Sustainability, MDPI, vol. 13(9), pages 1-13, May.
    5. Jianping Li & Lu Wei & Cheng-Few Lee & Xiaoqian Zhu & Dengsheng Wu, 2018. "Financial statements based bank risk aggregation," Review of Quantitative Finance and Accounting, Springer, vol. 50(3), pages 673-694, April.
    6. Zhiyong Li & Xinyi Hu & Ke Li & Fanyin Zhou & Feng Shen, 2020. "Inferring the outcomes of rejected loans: an application of semisupervised clustering," Journal of the Royal Statistical Society Series A, Royal Statistical Society, vol. 183(2), pages 631-654, February.
    7. Yu, Lean & Zhang, Xiaoming, 2021. "Can small sample dataset be used for efficient internet loan credit risk assessment? Evidence from online peer to peer lending," Finance Research Letters, Elsevier, vol. 38(C).
    8. Ata Allah Taleizadeh & Aria Zaker Safaei & Arijit Bhattacharya & Alireza Amjadian, 2022. "Online peer-to-peer lending platform and supply chain finance decisions and strategies," Annals of Operations Research, Springer, vol. 315(1), pages 397-427, August.
    9. Yanhong Guo & Shuai Jiang & Wenjun Zhou & Chunyu Luo & Hui Xiong, 2021. "A predictive indicator using lender composition for loan evaluation in P2P lending," Financial Innovation, Springer;Southwestern University of Finance and Economics, vol. 7(1), pages 1-24, December.
    10. Xi Yang & Wenjuan Fan & Shanlin Yang, 2020. "Identifying the Influencing Factors on Investors’ Investment Behavior: An Empirical Study Focusing on the Chinese P2P Lending Market," Sustainability, MDPI, vol. 12(13), pages 1-21, July.
    11. Zhao Wang & Cuiqing Jiang & Huimin Zhao, 2022. "Know Where to Invest: Platform Risk Evaluation in Online Lending," Information Systems Research, INFORMS, vol. 33(3), pages 765-783, September.
    12. Xiaoqian Zhu & Jianping Li & Dengsheng Wu, 2019. "Should the Advanced Measurement Approach for Operational Risk be Discarded? Evidence from the Chinese Banking Industry," Review of Pacific Basin Financial Markets and Policies (RPBFMP), World Scientific Publishing Co. Pte. Ltd., vol. 22(01), pages 1-15, March.
    13. Ligang Zhou & Chao Ma, 2023. "A Comparison of Different Rules on Loans Evaluation in Peer-to-Peer Lending by Gradient Boosting Models Under Moving Windows with Two Timestamps," Computational Economics, Springer;Society for Computational Economics, vol. 62(4), pages 1481-1504, December.
    14. Yufei Xia & Lingyun He & Yinguo Li & Nana Liu & Yanlin Ding, 2020. "Predicting loan default in peer‐to‐peer lending using narrative data," Journal of Forecasting, John Wiley & Sons, Ltd., vol. 39(2), pages 260-280, March.
    15. Xuchen Lin & Xiaolong Li & Zhong Zheng, 2017. "Evaluating borrower’s default risk in peer-to-peer lending: evidence from a lending platform in China," Applied Economics, Taylor & Francis Journals, vol. 49(35), pages 3538-3545, July.
    16. Qizhi Tao & Yizhe Dong & Ziming Lin, 2017. "Who can get money? Evidence from the Chinese peer-to-peer lending platform," Information Systems Frontiers, Springer, vol. 19(3), pages 425-441, June.
    17. Božović, Miloš & Ivanović, Jelena, 2017. "Adverse risk interaction: An integrated approach," Economic Modelling, Elsevier, vol. 65(C), pages 67-74.
    18. Yuzhen Ma & Xinyang Wei & Gaoyun Yan & Xiaoyu He, 2023. "The Impact of Fintech Development on Air Pollution," IJERPH, MDPI, vol. 20(4), pages 1-16, February.
    19. Gaigalienė Asta & Česnys Dovydas, 2018. "Determinants of Default in Lithuanian Peer-To-Peer Platforms," Management of Organizations: Systematic Research, Sciendo, vol. 80(1), pages 19-36, December.
    20. Dimitris Andriosopoulos & Michalis Doumpos & Panos M. Pardalos & Constantin Zopounidis, 2019. "Computational approaches and data analytics in financial services: A literature review," Journal of the Operational Research Society, Taylor & Francis Journals, vol. 70(10), pages 1581-1599, October.

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:arx:papers:2308.03704. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: arXiv administrators (email available below). General contact details of provider: http://arxiv.org/ .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.