Journal Home > Volume 6 , Issue 4
Big Data Mining and Analytics 2023, 6(4): 478-490 https://doi.org/10.26599/BDMA.2022.9020037
Open Access | Issue | Published: 29 August 2023

AI-Based Hybrid Models for Predicting Loan Risk in the Banking Sector

Show Author's Information Vikas Kumar1( ),  Shaiku Shahida Saheb2,  Preeti3,  Atif Ghayas4,  Sunil Kumari5,  Jai Kishan Chandel6,  Saroj Kumar Pandey7,  Santosh Kumar8
Humanities and Management Department, Dr. B. R. Ambedkar National Institute of Technology Jalandhar, Jalandhar 144027, India
Mittal School of Business, Lovely Professional University, Phagwara 144402, India
Department of Commerce & Business Administration, Kanya Maha Vidyalaya (KMV), Jalandhar 144004, India
School of Management, Gitam (to be deemed university), Bangalore 561203, India
Government College for Women, Indra Gandhi University, Ateli 123021, India
Institute of Management Studies, Kurukshetra University, Kurukshetra 136119, India
Department of Computer Engineering and Applications, GLA University, Mathura 281406, India
Department of Management, Jaipuriya Institute of Management, Jaipur 302033, India
Keywords:
Machine Learning (ML), Support Vector Machine (SVM), Artificial Intelligence (AI), accuracy, loan prediction, Random Forest (RF)
Cite this article:
Kumar V, Saheb SS, Preeti, et al. AI-Based Hybrid Models for Predicting Loan Risk in the Banking Sector. Big Data Mining and Analytics, 2023, 6(4): 478-490. https://doi.org/10.26599/BDMA.2022.9020037
Download citation
EndNote(RIS)
BibTeX

283

Views

52

Downloads

Citations

2

Crossref

0

WoS

1

Scopus

0

CSCD

Abstract Full text About this article

Every real-world scenario is now digitally replicated in order to reduce paperwork and human labor costs. Machine Learning (ML) models are also being used to make predictions in these applications. Accurate forecasting requires knowledge of these machine learning models and their distinguishing features. The datasets we use as input for each of these different types of ML models, yielding different results. The choice of an ML model for a dataset is critical. A loan risk model is used to show how ML models for a dataset can be linked together. The purpose of this study is to look into how we could use machine learning to quantify or forecast mortgage credit risk. This phrase refers to the process of evaluating massive amounts of data in order to derive useful information for making decisions in a variety of fields. If credit risk is considered, a method based on an examination of what caused and how mortgage credit risk affected credit defaults during the still-current economic crisis of 2021 will be tried. Various approaches to credit risk calculation will be examined, ranging from the most basic to the most complex. In addition, we will conduct a case study on a sample of mortgage loans and compare the results of three different analytical approaches, logistic regression, decision tree, and gradient boost to see which one produced the most commercially useful insights.


menu
Abstract
Full text
Outline
About this article

AI-Based Hybrid Models for Predicting Loan Risk in the Banking Sector

Show Author's information Vikas Kumar1( ), Shaiku Shahida Saheb2,  Preeti3, Atif Ghayas4, Sunil Kumari5, Jai Kishan Chandel6, Saroj Kumar Pandey7, Santosh Kumar8
Humanities and Management Department, Dr. B. R. Ambedkar National Institute of Technology Jalandhar, Jalandhar 144027, India
Mittal School of Business, Lovely Professional University, Phagwara 144402, India
Department of Commerce & Business Administration, Kanya Maha Vidyalaya (KMV), Jalandhar 144004, India
School of Management, Gitam (to be deemed university), Bangalore 561203, India
Government College for Women, Indra Gandhi University, Ateli 123021, India
Institute of Management Studies, Kurukshetra University, Kurukshetra 136119, India
Department of Computer Engineering and Applications, GLA University, Mathura 281406, India
Department of Management, Jaipuriya Institute of Management, Jaipur 302033, India

Abstract

Every real-world scenario is now digitally replicated in order to reduce paperwork and human labor costs. Machine Learning (ML) models are also being used to make predictions in these applications. Accurate forecasting requires knowledge of these machine learning models and their distinguishing features. The datasets we use as input for each of these different types of ML models, yielding different results. The choice of an ML model for a dataset is critical. A loan risk model is used to show how ML models for a dataset can be linked together. The purpose of this study is to look into how we could use machine learning to quantify or forecast mortgage credit risk. This phrase refers to the process of evaluating massive amounts of data in order to derive useful information for making decisions in a variety of fields. If credit risk is considered, a method based on an examination of what caused and how mortgage credit risk affected credit defaults during the still-current economic crisis of 2021 will be tried. Various approaches to credit risk calculation will be examined, ranging from the most basic to the most complex. In addition, we will conduct a case study on a sample of mortgage loans and compare the results of three different analytical approaches, logistic regression, decision tree, and gradient boost to see which one produced the most commercially useful insights.

Keywords: Machine Learning (ML), Support Vector Machine (SVM), Artificial Intelligence (AI), accuracy, loan prediction, Random Forest (RF)

References(22)

[1]
H. A. Abdou, S. Mitra, J. Fry, and A. A. Elamer, Would two-stage scoring models alleviate bank exposure to bad debt? Expert Systems with Applications, vol. 128, pp. 1–13, 2019.
DOI Google Scholar
[2]
D. Bülbül, H. Hakenes, and C. Lambert, What influences banks’ choice of credit risk management practices? Theory and evidence, Journal of Financial Stability, vol. 40, pp. 1–14, 2019.
DOI Google Scholar
[3]
A. E. Celik and Y. Karatepe, Evaluating and forecasting banking crises through neural network models: An application for Turkish banking sector, Expert Systems with Applications, vol. 33, no. 4, pp. 809–815, 2007.
DOI Google Scholar
[4]
J. Chen, A. L. Katchova, and C. X. Zhou, Agricultural loan delinquency prediction using machine learning methods, International Food and Agribusiness Management Review, vol. 24, no. 5, pp. 797–812, 2021.
DOI Google Scholar
[5]
A. Cozarenco and A. Szafarz, The regulation of prosocial lending: Are loan ceilings effective? Journal of Banking & Finance, vol. 121, p. 105979, 2020.
DOI Google Scholar
[6]
J. C. Cuestas, Y. Lucotte, and N. Reigl, Banking sector concentration, competition and financial stability: The case of the baltic countries, Post-Communist Economies, vol. 32, no. 2, pp. 215–249, 2020.
DOI Google Scholar
[7]
H. D. Silva, E. J. Dockner, R. Jankowitsch, S. Pichler, and K. Ritzberger, Choice of rating technology and loan pricing in imperfect credit markets, Journal of Risk, vol. 17, no. 1, pp. 29–62, 2014.
DOI Google Scholar
[8]
S. K. Depren and M. T. Kartal, Prediction on the volume of non-performing loans in Turkey using multivariate adaptive regression splines approach, International Journal of Finance & Economics, vol. 26, no. 4, pp. 6395–6405, 2021.
DOI Google Scholar
[9]
A. M. Dima and S. Vasilache, Credit risk modeling for companies default prediction using neural networks, Romanian Journal of Economic Forecasting, vol. 19, no. 3, pp. 127–143, 2016.
Google Scholar
[10]
G. Enjolras and P. Madies, The role of bank analysts and scores in the prediction of financial distress: Evidence from French farms, Economics Bulletin, vol. 40, no. 4, pp. 2978–2993, 2020.
Google Scholar
[11]
P. Gandhi, T. Loughran, and B. McDonald, Using annual report sentiment as a proxy for financial distress in US banks, Journal of Behavioral Finance, vol. 20, no. 4, pp. 424–436, 2019.
DOI Google Scholar
[12]
K. Halteh, K. Kumar, and A. Gepp, Using cutting-edge tree-based stochastic models to predict credit risk, Risks, vol. 6, no. 2, p. 55, 2018.
DOI Google Scholar
[13]
Z. Y. Li, J. Crook, and G. Andreeva, Dynamic prediction of financial distress using malmquist DEA, Expert Systems with Applications, vol. 80, pp. 94–106, 2017.
DOI Google Scholar
[14]
S. Mall, An empirical study on credit risk management: The case of nonbanking financial companies, Journal of Credit Risk, vol. 14, no. 3, pp. 49–66, 2018.
DOI Google Scholar
[15]
A. Martin-Oliver, S. Ruano, and V. Salas-Fumás, How does bank competition affect credit risk? Evidence from loan-level data, Economics Letters, vol. 196, p. 109524, 2020.
DOI Google Scholar
[16]
S. Pokrason, A healthy dose of pessimism? Influence of the Ukrainian economy on its banking sector credit ratings, Baltic Journal of Economic Studies, vol. 3, no. 4, pp. 216–223, 2017.
DOI Google Scholar
[17]
Preeti and S. Roy, Application of hybrid approach in banking system: An undesirable operational performance modelling, Global Business Review, .
DOI Google Scholar
[18]
W. W. Qiu, Enterprise financial risk management platform based on 5G mobile communication and embedded system, Microprocessors and Microsystems, vol. 80, p. 103594, 2021.
DOI Google Scholar
[19]
P. Saha, I. Bose, and A. Mahanti, A knowledge based scheme for risk assessment in loan processing by banks, Decision Support Systems, vol. 84, pp. 78–88, 2016.
DOI Google Scholar
[20]
V. Srivastava, Distressed debt investments in India: What more needs to be done to strengthen regulations? International Journal of Indian Culture and Business Management, vol. 18, no. 3, pp. 368–380, 2019.
DOI Google Scholar
[21]
H. A. Abdou, M. D. D. Tsafack, C. G. Ntim, and R. D. Baker, Predicting creditworthiness in retail banking with limited scoring data, Knowledge-Based Systems, vol. 103, pp. 89–103, 2016.
DOI Google Scholar
[22]
A. Bhimani, M. A. Gulamhussen, and S. D. R. Lopes, Accounting and non-accounting determinants of default: An analysis of privately-held firms, Journal of Accounting and Public Policy, vol. 29, no. 6, pp. 517–532, 2010.
DOI Google Scholar
Publication history
Copyright
Rights and permissions

Publication history

Received: 17 May 2022
Revised: 01 September 2022
Accepted: 07 October 2022
Published: 29 August 2023
Issue date: December 2023

Copyright

© The author(s) 2023.

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).

Return