Advertisement

The Journal of Supercomputing

, Volume 75, Issue 2, pp 862–884 | Cite as

Transfer learning-based default prediction model for consumer credit in China

  • Wei Li
  • Shuai DingEmail author
  • Yi Chen
  • Hao Wang
  • Shanlin YangEmail author
Article
  • 261 Downloads

Abstract

Financial institutions in China, such as banks, are encountering competitive impacts from Internet financial businesses. To address these impacts, financial institutions are seeking business innovations, such as an automatic credit evaluation system that is based on machine learning. Abundant new credit data are required in the implementation of new businesses to establish related risk evaluation models; however, new businesses lack data. Based on these insights, this paper innovatively proposes the idea of transfer learning, determines the similarity between traditional businesses and new businesses and transfers the data of traditional bank businesses to new business data to construct new training sets and to train small data sets. The reconstructed training data sets are used to train default risk prediction models, compare them with the benchmark models in the tests and validate the performance and adaptation of the default prediction model based on transfer learning technique. Our study highlights the commercial value of the transfer learning concept in the financial risk field and provides practitioners and management personnel with a decision basis.

Keywords

Default prediction Transfer learning Consumer credit Small sample Data driven 

Notes

Acknowledgements

This work was funded by the National Natural Science Foundation of China under Grant Nos. 71571058 and 71690235, and Anhui Provincial Science and Technology Major Project under Grant Nos. 16030801121 and 17030801001.

References

  1. 1.
    Ding S, Wang Z, Wu D, Olson DL (2017) Utilizing customer satisfaction in ranking prediction for personalized cloud service selection. Decision Support Syst 93:1–10.  https://doi.org/10.1016/j.dss.2016.09.001 CrossRefGoogle Scholar
  2. 2.
    Miao H, Ramchander S, Ryan P, Wang T (2018) Default prediction models: the role of forward-looking measures of returns and volatility. J Empir Finance 46:146–162.  https://doi.org/10.1016/j.jempfin.2018.01.001 CrossRefGoogle Scholar
  3. 3.
    Barboza F, Kimura H, Altman E (2017) Machine learning models and bankruptcy prediction. Expert Syst Appl 83:405–417.  https://doi.org/10.1016/j.eswa.2017.04.006 CrossRefGoogle Scholar
  4. 4.
    Maldonado S, Peters G, Weber R (2018) Credit scoring using three-way decisions with probabilistic rough sets. Inf Sci (Ny) 0:1–15.  https://doi.org/10.1016/j.ins.2018.08.001 Google Scholar
  5. 5.
    Zheng C, Xia C, Guo Q, Dehmer M (2018) Interplay between SIR-based disease spreading and awareness diffusion on multiplex networks. J Parallel Distrib Comput 115:20–28.  https://doi.org/10.1016/j.jpdc.2018.01.001 CrossRefGoogle Scholar
  6. 6.
    Jeon J, Yoon JH, Park CR (2018) The pricing of dynamic fund protection with default risk. J Comput Appl Math 333:116–130.  https://doi.org/10.1016/j.cam.2017.10.031 MathSciNetCrossRefzbMATHGoogle Scholar
  7. 7.
    Wei X, Luo X, Li Q et al (2015) Online comment-based hotel quality automatic assessment using improved fuzzy comprehensive. IEEE Trans Fuzzy Syst 23:72–84CrossRefGoogle Scholar
  8. 8.
    Jiang H, Ching WK, Yiu KFC, Qiu Y (2018) Stationary Mahalanobis kernel SVM for credit risk evaluation. Appl Soft Comput J 71:407–417.  https://doi.org/10.1016/j.asoc.2018.07.005 CrossRefGoogle Scholar
  9. 9.
    Maldonado S, Bravo C, López J, Pérez J (2017) Integrated framework for profit-based feature selection and SVM classification in credit scoring. Decision Support Syst 104:113–121.  https://doi.org/10.1016/j.dss.2017.10.007 CrossRefGoogle Scholar
  10. 10.
    Pang X, Zhou Y, Wang P et al (2018) An innovative neural network approach for stock market prediction. J Supercomput.  https://doi.org/10.1007/s11227-017-2228-y Google Scholar
  11. 11.
    Pan SJ, Yang Q (2010) A survey on transfer learning. IEEE Trans Knowl Data Eng 22:1345–1359.  https://doi.org/10.1109/TKDE.2009.191 CrossRefGoogle Scholar
  12. 12.
    Tian S, Yu Y (2017) Financial ratios and bankruptcy predictions: an international evidence. Int Rev Econ Finance 51:510–526.  https://doi.org/10.1016/j.iref.2017.07.025 CrossRefGoogle Scholar
  13. 13.
    Ciampi F (2015) Corporate governance characteristics and default prediction modeling for small enterprises. An empirical analysis of Italian firms. J Bus Res 68:1012–1025.  https://doi.org/10.1016/j.jbusres.2014.10.003 CrossRefGoogle Scholar
  14. 14.
    Ma L, Zhao X, Zhou Z, Liu Y (2018) A new aspect on P2P online lending default prediction using meta-level phone usage data in China. Decision Support Syst.  https://doi.org/10.1016/j.dss.2018.05.001 Google Scholar
  15. 15.
    Tkáč M, Verner R (2015) Artificial neural networks in business: two decades of research. Appl Soft Comput 38:788–804.  https://doi.org/10.1016/j.asoc.2015.09.040 Google Scholar
  16. 16.
    Krauss C, Do XA, Huck N (2017) Deep neural networks, gradient-boosted trees, random forests: statistical arbitrage on the S&P 500. Eur J Oper Res 259:689–702.  https://doi.org/10.1016/j.ejor.2016.10.031 CrossRefzbMATHGoogle Scholar
  17. 17.
    Zhou L, Si YW, Fujita H (2017) Predicting the listing statuses of Chinese-listed companies using decision trees combined with an improved filter feature selection method. Knowl Based Syst 128:93–101.  https://doi.org/10.1016/j.knosys.2017.05.003 CrossRefGoogle Scholar
  18. 18.
    Yao X, Crook J, Andreeva G (2015) Support vector regression for loss given default modelling. Eur J Oper Res 240:528–538.  https://doi.org/10.1016/j.ejor.2014.06.043 MathSciNetCrossRefzbMATHGoogle Scholar
  19. 19.
    Gordini N (2014) A genetic algorithm approach for SMEs bankruptcy prediction: empirical evidence from Italy. Expert Syst Appl 41:6433–6445.  https://doi.org/10.1016/j.eswa.2014.04.026 CrossRefGoogle Scholar
  20. 20.
    Arar ÖF, Ayan K (2017) A feature dependent Naive Bayes approach and its application to the software defect prediction problem. Appl Soft Comput J 59:197–209.  https://doi.org/10.1016/j.asoc.2017.05.043 CrossRefGoogle Scholar
  21. 21.
    Sun J, Lang J, Fujita H, Li H (2017) Imbalanced enterprise credit evaluation with DTE-SBD: decision tree ensemble based on SMOTE and bagging with differentiated sampling rates. Inf Sci (Ny) 425:76–91.  https://doi.org/10.1016/j.ins.2017.10.017 MathSciNetCrossRefGoogle Scholar
  22. 22.
    Yu L, Zhou R, Tang L, Chen R (2018) A DBN-based resampling SVM ensemble learning paradigm for credit classification with imbalanced data. Appl Soft Comput J 69:192–202.  https://doi.org/10.1016/j.asoc.2018.04.049 CrossRefGoogle Scholar
  23. 23.
    Wang D, Zhang Z, Bai R, Mao Y (2018) A hybrid system with filter approach and multiple population genetic algorithm for feature selection in credit scoring. J Comput Appl Math 329:307–321.  https://doi.org/10.1016/j.cam.2017.04.036 MathSciNetCrossRefzbMATHGoogle Scholar
  24. 24.
    Sohn SY, Kim DH, Yoon JH (2016) Technology credit scoring model with fuzzy logistic regression. Appl Soft Comput J 43:150–158.  https://doi.org/10.1016/j.asoc.2016.02.025 CrossRefGoogle Scholar
  25. 25.
    Guo Y, Zhou W, Luo C et al (2016) Instance-based credit risk assessment for investment decisions in P2P lending. Eur J Oper Res 249:417–426.  https://doi.org/10.1016/j.ejor.2015.05.050 MathSciNetCrossRefzbMATHGoogle Scholar
  26. 26.
    Hurlin C, Leymarie J, Patin A (2018) Loss functions for loss given default model comparison. Eur J Oper Res 268:348–360.  https://doi.org/10.1016/j.ejor.2018.01.020 MathSciNetCrossRefzbMATHGoogle Scholar
  27. 27.
    Pan W-T, Huang C-E, Chiu C-L (2016) Study on the performance evaluation of online teaching using the quantile regression analysis and artificial neural network. J Supercomput 72:789–803.  https://doi.org/10.1007/s11227-015-1599-1 CrossRefGoogle Scholar
  28. 28.
    Feng X, Xiao Z, Zhong B et al (2018) Dynamic ensemble classification for credit scoring using soft probability. Appl Soft Comput J 65:139–151.  https://doi.org/10.1016/j.asoc.2018.01.021 CrossRefGoogle Scholar
  29. 29.
    Ye R, Dai Q (2018) A novel transfer learning framework for time series forecasting. Knowl Based Syst 156:74–99.  https://doi.org/10.1016/j.knosys.2018.05.021 CrossRefGoogle Scholar
  30. 30.
    Nasiri M, Minaei B (2016) Increasing prediction accuracy in collaborative filtering with initialized factor matrices. J Supercomput 72:2157–2169.  https://doi.org/10.1007/s11227-016-1717-8 CrossRefGoogle Scholar
  31. 31.
    Lu J, Behbood V, Hao P et al (2015) Transfer learning using computational intelligence: a survey. Knowl Based Syst 80:14–23.  https://doi.org/10.1016/j.knosys.2015.01.010 CrossRefGoogle Scholar
  32. 32.
    Zhu Y, Hu X, Zhang Y, Li P (2018) Transfer learning with stacked reconstruction independent component analysis. Knowl Based Syst 152:100–106.  https://doi.org/10.1016/j.knosys.2018.04.010 CrossRefGoogle Scholar
  33. 33.
    Ding S, Li Y, Wu D et al (2018) Time-aware cloud service recommendation using similarity-enhanced collaborative filtering and ARIMA model. Decision Support Syst 107:103–115.  https://doi.org/10.1016/j.dss.2017.12.012 CrossRefGoogle Scholar
  34. 34.
    Wang J, Ding S, Song M et al (2018) Smart community evaluation for sustainable development using a combined analytical framework. J Clean Prod 193:158–168.  https://doi.org/10.1016/j.jclepro.2018.05.023 CrossRefGoogle Scholar
  35. 35.
    Wang Y, Zhai J, Li Y et al (2018) Transfer learning with partial related “instance-feature” knowledge. Neurocomputing 310:115–124.  https://doi.org/10.1016/j.neucom.2018.05.029 CrossRefGoogle Scholar
  36. 36.
    Xia C, Ding S, Wang C et al (2017) Risk analysis and enhancement of cooperation yielded by the individual reputation in the spatial public goods game. IEEE Syst J 11:1516–1525.  https://doi.org/10.1109/JSYST.2016.2539364 CrossRefGoogle Scholar
  37. 37.
    Xia Y, Liu C, Da B, Xie F (2018) A novel heterogeneous ensemble credit scoring model based on bstacking approach. Expert Syst Appl 93:182–199.  https://doi.org/10.1016/j.eswa.2017.10.022 CrossRefGoogle Scholar
  38. 38.
    He H, Zhang W, Zhang S (2018) A novel ensemble method for credit scoring: adaption of different imbalance ratios. Expert Syst Appl 98:105–117.  https://doi.org/10.1016/j.eswa.2018.01.012 CrossRefGoogle Scholar
  39. 39.
    Haixiang G, Yijing L, Shang J et al (2017) Learning from class-imbalanced data: review of methods and applications. Expert Syst Appl 73:220–239.  https://doi.org/10.1016/j.eswa.2016.12.035 CrossRefGoogle Scholar
  40. 40.
    Xia Y, Liu C, Li Y, Liu N (2017) A boosted decision tree approach using Bayesian hyper-parameter optimization for credit scoring. Expert Syst Appl 78:225–241.  https://doi.org/10.1016/j.eswa.2017.02.017 CrossRefGoogle Scholar
  41. 41.
    Ma X, Sha J, Wang D et al (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. Electron Commer Res Appl.  https://doi.org/10.1016/j.elerap.2018.08.002 Google Scholar
  42. 42.
    Ke G, Meng Q, Wang T et al (2017) LightGBM: a highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst 30:3148–3156Google Scholar
  43. 43.
    Fujita K, Takewaki I (2011) An efficient methodology for robustness evaluation by advanced interval analysis using updated second-order Taylor series expansion. Eng Struct 33:3299–3310.  https://doi.org/10.1016/j.engstruct.2011.08.029 CrossRefGoogle Scholar
  44. 44.
    Diwakaran S, Perumal B, Vimala Devi K (2018) A cluster prediction model-based data collection for energy efficient wireless sensor network. J Supercomput.  https://doi.org/10.1007/s11227-018-2437-z Google Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  1. 1.School of ManagementHefei University of TechnologyHefeiChina
  2. 2.Key Laboratory of Process Optimization and Intelligent Decision-Making (Ministry of Education)Hefei University of TechnologyHefeiChina

Personalised recommendations