XAI - Credit Risk Analysis | [International Journal of Communication Networks and Information Security • 2024]

Author(s):

1. Nilesh Patil: Computer Engineering, Dwarkadas J. Sanghvi College of Engineering,Mumbai,India

2. Sridhar Iyer: Computer Engineering, Dwarkadas J. Sanghvi College of Engineering,Mumbai,India

3. Chaitya Lakhani: Computer Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India

4. Param Shah: Computer Engineering, Dwarkadas J. Sanghvi College of Engineering, Mumbai, India

Abstract:

This paper delves into the integration of Explainable AI (XAI) techniques with machine learning models for credit risk classification, addressing the critical issue of model transparency in financial services. We experimented with various models, including Logistic Regression, Random Forest, XGBoost, LightGBM, and Artificial Neural Networks (ANN), on real-world credit datasets to predict borrower risk levels. Our results show that while ANN achieved the highest accuracy at 95.3%, Random Forest followed closely with 95.23%. Logistic Regression also performed strongly with an accuracy of 94.68%, while XGBoost and LightGBM delivered slightly lower accuracies of 94.4% and 94.37%, respectively. However, the superior accuracy of these complex models, particularly ANN, comes with a trade-off: reduced transparency, making it difficult for stakeholders to understand the decision-making process. To address this, we applied XAI techniques such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations) to provide clear and understandable explanations for the predictions made by these models. This integration not only enhanced model interpretability but also built trust among stakeholders and ensured compliance with regulatory standards. This study illustrates how XAI serves as an effective mediator between the precision of sophisticated machine learning algorithms and the demand for clarity in evaluating credit risk. XAI offers a well-balanced method for managing risk in finance, harmonizing the need for both accuracy and interpretability.

Page(s): 428-439

DOI: DOI not available

Published: Journal: International Journal of Communication Networks and Information Security, Volume: 16, Issue: 4, Year: 2024

Keywords:

Interpretable machine learning , Credit Risk , Financial Technology FinTech , Explainable artificial intelligence XAI

References:

[1] Chang V.,Xu Q.A.,Akinloye S.H. .2024 .Prediction of bank credit worthiness through credit risk analysis: An explainable machine learning study. Annals of Operations Research, : .

[2] Hoang D.,Wiegratz K. .2022 .Machine learning methods in finance: Recent applica- tions and prospects. European Financial Management, 17(December 2022) : .

[3] Misheva B.H.,Hirsa A.,Osterrieder J.,Kulkarni O.,Lin S.F. .2021 .Explainable ai in credit risk management (. A preprin., : 2103.

[4] Weber P.,Carl K.V.,Hinz O. .2024 .Applications of explainable artificial intelligence in finance-a systematic review of finance, information systems, and computer science literature. Management Review Quarterly, 74 : 867-907.

[5] Pandey T.N.,Jagadev A.K.,Mohapatra S.K.,Dehuri S. .2017 .Credit risk analysis using machine learning classifiers. In: 2017 International Conference on Energy, Communication, Data Analytics and Soft Computing (ICECDS), : 1850-1854.

[6] Hu Y.,Su J.: .2021 .: Developing Global Digital Economy after COVID-19. Procedia Computer Science, 01 : 1168-1176.

[7] Nallakaruppan M.K.,Balusamy B.,Shri M.L.,Malathi V.,Bhattacharyya S.:,Shiam S.,Hasan M.,Pantho M.,Shochona S.,Nayeem M.B.,Choudhury M.T.H.,Nguyen T. .2024 .Credit risk prediction using explainable ai. Journal of Busi- ness and Management Studies, 6(2) : 6-66.

[8] Meenakshi B.,Jhansi A.,Sri M.R.,Chandra K.R. .2024 .Enhancing loan predic- tion accuracy: A comparative analysis of machine learning algorithms with xai integration. International Journal of Scientific Research in Engineering and Man- agement (IJSREM) 8, 8(5) : 44-7.

[9] Lange P.E.,Melsom B.,Vennerød C.B.,Westgaard S. .2022 .Explainable ai for credit assessment in banks. Journal of Risk and Financial Management, 15(12) : .

[10] Ayad O.M.,Hegazy A.-E.F.,Dahroug A. .2024 .A proposed model for loan approval prediction using xai. International Journal of Scientific Research in Engineer- ing and Management (IJSREM) 8, 8(5) : 448-7.

[11] .2021 .Credit risk analysis using machine-learning algorithms. In: 2021 29th Signal Processing and Communications Applications Conference (SIU), : 1-4.

[12] Dutta G. .2024 .-analytics-in-banking-financial-services-1. Accessed: April, 10 : .

Citations

Downloads

Views