Deep Learning in Risk Assessment

  • Janayna Fernandes Universidade Federal de Uberlândia
  • Lucas Bissaro Universidade Federal de Uberlândia
  • Fernanda Santos Universidade Federal de Uberlândia
  • Murillo Carneiro Universidade Federal de Uberlândia

Resumo


Credit evaluation models have been largely studied in the accounting and finance literature. With the support of such models, usually developed as part of a data mining process, it is possible to classify the credit applicants more accurately into "good" or "bad" risk groups. Despite many machine learning techniques have been extensively evaluated to this problem, deep learning models have been barely explored yet, although they have provided state-of-the-art results for a myriad of applications. In this paper, we propose deep learning models for the credit evaluation problem. To be specific, we investigate the abilities of deep neural networks (DNN) and convolutional neural networks (CNN) for such a problem and systematically compare their classification accuracy against five commonly adopted techniques on three real-world credit evaluation datasets. The results show that random forest, which is a state-of-the-art technique for such a problem, presented the most consistent performance, although CNN demonstrated a high potential to outperform it in bigger datasets.

Palavras-chave: Deep Learning, Credit risk, Machine Learning, Credit data

Referências

Asuncion, A. and Newman, D. (2007). UCI machine learning repository.

Baesens, B., Van Gestel, T., Viaene, S., Stepanova, M., Suykens, J., and Vanthienen, J. (2003). Benchmarking state-of-the-art classification algorithms for credit scoring. Journal of the operational research society, 54(6):627–635.

Canziani, A., Paszke, A., and Culurciello, E. (2016). An analysis of deep neural network models for practical applications. CoRR, abs/1605.07678.

Cao, Y. (2018). Deep learning based RGB-D vision tasks. PhD thesis.

Carneiro, M. G. and Gabriel, A. (2018). What’s the next move? learning player strategies in zoom poker games. In 2018 IEEE Congress on Evolutionary Computation (CEC), pages 1–8. IEEE.

Chen, J., Chen, W., Huang, C., Huang, S., and Chen, A. (2016). Financial time-series data analysis using deep convolutional neural networks. In 2016 7th International Conference on Cloud Computing and Big Data (CCBD), pages 87–92.

Chen, M.-C. and Huang, S.-H. (2003). Credit scoring and rejected instances reassigning through evolutionary computation techniques. Expert Systems with Applications, 24(4):433–441.

Deng, Y., Bao, F., Kong, Y., Ren, Z., and Dai, Q. (2016). Deep direct reinforcement learning for financial signal representation and trading. IEEE Transactions on Neural Networks and Learning Systems, 28(3):653–664.

Doshi, C. (2018). A deep learning approach to state estimation from videos. PhD thesis.

Hand, D. J. and Henley, W. E. (1997). Statistical classification methods in consumer credit scoring: a review. Journal of the Royal Statistical Society: Series A (Statistics in Society), 160(3):523–541.

LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. nature, 521(7553):436.

Lessmann, S., Baesens, B., Seow, H.-V., and Thomas, L. C. (2015). Benchmarking stateof-the-art classification algorithms for credit scoring: An update of research. European Journal of Operational Research, 247(1):124–136.

Li, Y., Lin, X., Wang, X., Shen, F., and Gong, Z. (2017). Credit risk assessment algorithm using deep neural networks with clustering and merging. In 2017 13th International Conference on Computational Intelligence and Security (CIS), pages 173–176.

Liao, Z. (2017). Methods for Understanding and Improving Deep Learning Classification Models. PhD thesis.

Lin, M., Chen, Q., and Yan, S. (2013). Network in network. CoRR, abs/1312.4400.

Simonyan, K. and Zisserman, A. (2015). Very deep convolutional networks for large-scale image recognition. In International Conference on Learning Representations.

Sinha, S., Singh, T., Singh, V., and Verma, A. (2010). Epoch determination for neural network by self-organized map (som). Computational Geosciences, 14(1):199–206.

Sun, T. and Vasarhelyi, M. A. (2018). Predicting credit card delinquencies: An application of deep neural networks. Intelligent Systems in Accounting, Finance and Management, 25(4):174–189.

Tan, P.-N. (2018). Introduction to data mining. Pearson Education India.

Wei, G., Yingjie, S., and Mu, Y. X. (2015). Commercial bank credit risk evaluation method based on decision tree algorithm. In Measuring Technology and Mechatronics Automation (ICMTMA), 2015 Seventh International Conference on, pages 285–288. IEEE.

Yeh, I.-C. and Lien, C.-h. (2009). The comparisons of data mining techniques for the predictive accuracy of probability of default of credit card clients. Expert Systems with Applications, 36(2):2473–2480.

Zhang, B. (2014). Deep learning with application to hashing. PhD thesis.

Zhang, D. and Zhou, L. (2004). Discovering golden nuggets: data mining in financial application. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 34(4):513–522.

Zhang, J. (2016). Deep learning for multi-label scene classification. PhD thesis.
Publicado
15/10/2019
FERNANDES, Janayna; BISSARO, Lucas; SANTOS, Fernanda; CARNEIRO, Murillo. Deep Learning in Risk Assessment. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 16. , 2019, Salvador. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2019 . p. 1068-1079. ISSN 2763-9061. DOI: https://doi.org/10.5753/eniac.2019.9358.