• ISSN: 2301-3567 (Print)
    • Abbreviated Title: J. Econ. Bus. Manag.
    • Frequency: Quarterly (2013-2014); Monthly (2015-2017); Quarterly (Since 2018)
    • DOI: 10.18178/JOEBM
    • Editor-in-Chief: Prof. Eunjin Hwang
    • Executive Editor: Ms. Mia Hu
    • Abstracting/ Indexing:  Electronic Journals Library, Ulrich's Periodicals Directory, MESLibrary, Google Scholar, and Crossref.
    • E-mail: joebm@ejournal.net
JOEBM 2019 Vol.7(3): 93-96 ISSN: 2301-3567
DOI: 10.18178/joebm.2019.7.3.588

Deep Learning Techniques for Credit Scoring

Le Quy Tai and Giang Thi Thu Huyen
Abstract—Credit scoring is a crucial phase in the risk management process of financial organizations and commercial banks. Deep Learning algorithms are the powerful techniques with significant improvements in classification performances in many applications of machine learning fields such as image processing and speech recognition. The key benefit of Deep Learning models is the ability to analyze and learn massive amounts of data. In this paper, we apply two deep learning architectures for credit scoring problem: 1) Sequential Deep Neural Network; 2) Convolutional Neural Network. Our experiments of three different datasets show that all the neural network performance better than traditional approaches.

Index Terms—Deep learning, neural network, credit scoring, CNN.

Le Quy Tai and Giang Thi Thu Huyen are with Banking Academy of Vietnam, Vietnam (e-mail: quytai3985@gmail.com, gianghuyenhvnh@gmail.com).

[PDF]

Cite:Le Quy Tai and Giang Thi Thu Huyen, "Deep Learning Techniques for Credit Scoring," Journal of Economics, Business and Management vol. 7, no. 3, pp. 93-96, 2019.

Copyright © 2008-2019. Journal of Economics, Business and Management. All rights reserved.
E-mail: joebm@ejournal.net