Abstract
Despite the increase in the practice and the advent of artificial neural networks (ANNs) and deep learning (DL) to reduce the number of slippage loans in the banking and financial industries, some of the Nigerian banks and financial institutions are not aware of its efficacy. Loan request assessment would expand credit pronouncement efficiency, and inadvertently save the time and cost associated with loan analysis. This research considered, compared, and contrasted two artificial neural networks algorithms –the Mini-batch (Normal) gradient descent and the stochastic gradient descent algorithms. Each of the algorithms was separately used with back-propagation neural networks to develop loan evaluation models. Samples were collected from a Nigerian bank, these samples contain an index of default and non-default customers, and were used to train the loan evaluation models. The outcomes of the research show that the stochastic gradient descent algorithm outperforms the mini-batch gradient descent algorithm in terms of the percentage accuracy (0.863 and 0.835 respectively) and the space complexity, while the mini-batch gradient descent algorithm performed better in time complexity (107 µs and 1 ms respectively). The stochastic gradient descent algorithm was superior in identifying borrowers that were default with 87% accuracy.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Grégoire, M., Geneviève, B., Klaus-Robert, M.: Neural Networks: Tricks of the Trade, vol. 7700(2), pp. 1611–3349. Springer (2012). https://doi.org/10.1007/978-3-642-35289-8
Wei, W., Zhou, B., Maskeliūnas, R., Damaševičius, R., Połap, D., Woźniak, M.: Iterative design and implementation of rapid gradient descent method. In: Rutkowski, L., Scherer, R., Korytkowski, M., Pedrycz, W., Tadeusiewicz, R., Zurada, J. (eds) Artificial Intelligence and Soft Computing. ICAISC 2019. Lecture Notes in Computer Science, vol 11508. Springer, Cham (2019)
Ha, S., Nguyen, H.: Credit scoring with a feature selection approach based on deep learning. In: MATEC Web of Conferences, vol. 54, 11–12 (2016). https://www.researchgate.net/publication/301594739_Credit_scoring_with_a_feature_selection_approach_based_deep_learning
Zeidan, R., Boechat, C., Fleury, A.: Developing a sustainability credit score system. J. Bus. Ethics 127(2), 283–296 (2014). https://doi.org/10.1007/s10551-013-2034-2
Crouhy, M., Galai, D., Mark, R.: A comparative analysis of current credit risk models. J. Bank. Finance 24(1–2), 59–117 (2000)
Jin, L., Jiang, S.: Comparison of gradient descent and least squares algorithms in deep model. In: Journal of Physics: Conference Series, vol. 1621, 1742–6596 (2020). https://www.researchgate.net/publication/344564611_Comparison_of_Gradient_Descent_and_Least_Squares_Algorithms_in_Deep_Model
Addo, P., Guegan, D., Hassani, B.: Credit risk analysis using machine and deep learning models. Risks 6(2), 38 (2018)
Conor, M.: Machine learning fundamentals. Cost functions and gradient descent. https://towardsdatascience.com/machine-learning-fundamentals-via-linear-regression-41a5d11f5220. Accessed 09 July 2021
Tiwari, K., Chong, N.: Gradient descent. Multi-robot Explor. Environ. Monitor. 1, 41–52 (2020). https://doi.org/10.1016/B978-0-12-817607-8.00018-6
Kirill, E.: Neural Networks in Python from Scratch: Complete Guide. https://www.superdatascience.com/courses/neural-networks-python, Accessed 09 Jun 2021
Michael, N.: Artificial Intelligence, 3e. University of Tasmania, school of electrical engineering and computer science (2012)
Wenrui, H.: A gradient descent method for solving a system of nonlinear equations. Appl. Math. Lett. 112, 1–8 (2021)
Eveline, N.: Credit risk management in banks as participants in financial markets. A qualitative study of the perception of bank managers in Sweden (Umeå region). Thesis, Umeå School of Business, Master thesis, 30 hp (2010). https://www.diva-portal.org/smash/get/diva2:441943/FULLTEXT02
Zhao, J., Zhang, R., Zhou, Z., Chen, S., Jin, J., Liu, Q.: A neural architecture search method based on gradient descent for remaining useful life estimation. Neurocomputing 438, 184–194 (2021)
Barani, F., Savadi, A., Yazdi, H.: Convergence behavior of diffusion stochastic gradient descent algorithm. Signal Process. 183, 108014 (2021)
Leo, M., Sharma, S., Maddulety, K.: Machine learning in banking risk management: a literature review. Risks. 7(1), 29 (2019)
Addo, P., Guegan, D., Hassani, B.: Credit Risk Analysis Using Machine and Deep Learning Models. SSRN Electr. J. 10, 2139 (2018)
Rehman, G., Syed, M., Mohd, N.: Improving the accuracy of gradient descent back propagation algorithm (GDAM) on classification problems. Int. J. New Comput. Arch. Appl. 4(4), 861–870 (2011)
Deng, C., Lin, H.: Progressive and iterative approximation for least-squares B-spline curve and surface fitting. Comput. Aided Des. 47(1), 32–44 (2014)
Rios, D., Jüttler, B.: LSPIA, (stochastic) gradient descent, and parameter correction, 113921, 1–18 (2021)
Julia, K.: Credit Rating. https://www.investopedia.com/terms/c/creditrating.asp. Assessed 09 July 2021
Misra, S.: A step by step guide for choosing project topics and writing research papers in ICT related disciplines. In: Misra, S., Muhammad-Bello, B. (eds.) Information and Communication Technology and Applications. ICTA 2020. Communications in Computer and Information Science, vol. 1350. Springer, Cham (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Adigun, A.A., Yinka-Banjo, C. (2022). Comparing Stochastic Gradient Descent and Mini-batch Gradient Descent Algorithms in Loan Risk Assessment. In: Misra, S., Oluranti, J., Damaševičius, R., Maskeliunas, R. (eds) Informatics and Intelligent Applications. ICIIA 2021. Communications in Computer and Information Science, vol 1547. Springer, Cham. https://doi.org/10.1007/978-3-030-95630-1_20
Download citation
DOI: https://doi.org/10.1007/978-3-030-95630-1_20
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-95629-5
Online ISBN: 978-3-030-95630-1
eBook Packages: Computer ScienceComputer Science (R0)