11, November 2025

Assessment of Efficiency of Machine Learning Algorithms in Loan-Default Prediction

VOLUME-7; ISSUE-11; NOV-2025

Author(s): Sanjay Gour, Vaibhav Khanna

Authors Affiliations:

1, 2 Department of Computer Science,

Maharshi Dayanand Saraswati University, Ajmer, Rajasthan

DOIs:10.2019/IJEDI/202511001     |     Paper ID: IJEDI202511001


Abstract
Keywords
Cite this Article/Paper as
References

Abstract: Nowadays the loan default prediction is one of the crucial jobs for the institutions which are financially associated. This activity is unswervingly inducing risk management, approval of loan decisions, along with the profitability. Although there are lot of parameters by which traditionally financial institutions are predicting the loan defaults, but these approaches are not enough to handle properly. Also, there is strong need to not to approve the loan to the person who will be loan defaulter. This study focused on the effectiveness of the various machine learning algorithms models including Random Forest, Gradient Boosting, XGBoost and LightGBM. To solve the problem an organized machine learning approach is established, together with data preprocessing, feature engineering, class imbalance handling, model training and evaluation. The implemented models are evaluated by utilising the matrix of accuracy, F1-score, ROC-AUC, Precision and Recall. This paper is an attempt to synchronised with dataset by the appropriate machine learning algorithms to predict the loan default in the efficient manner by using various evaluation matrix.

     
Keywords: Machine Learning, Loan Default, Random Forest, XGBoost, LightGBM.

Sanjay Gour, Vaibhav Khanna (2025); Assessment of Efficiency of Machine Learning Algorithms in Loan-Default Prediction,  International Journal of Engineering and Designing Innovation (IJEDI), Vol-7, Issue-5,  Pp. 1-5.      Available on –  https://jedi.researchculturesociety.org/,

  1. Zhang,X., Zhang,T. ,Hou, L., Liu, X., Guo, Z., Tian, Y. and Liu, Y. (2025), Data-Driven Loan Default Prediction: A Machine Learning Approach for Enhancing Business Process Management, MDPI Systems 2025, vol-13, no-581. https://doi.org/10.3390/ systems13070581
  2. Lin Zhua, Dafeng Qiua , Daji Ergua, Cai Yinga, and Kuiyi Liub (2019), A study on predicting loan default based on the random forest algorithm, ELSEVIER-Procedia Computer Science, Science Direct, vol- 162 (2019), Pp-503–513.
  3. Zhi Zheng Kang , Teh Sin Yin, Samuel Yong Guang Tan and Wei Chien Ng (2025), Loan Default Prediction Using Machine Learning Algorithms, Journal of Informatics and Web Engineering, vol- 4, no-3, Pp-232-244,  DOI:33093/jiwe.2025.4.3.14
  4. Luca Barbaglia, Sebastiano Manzan and Elisa Tosetti (2023), Forecasting Loan Default in Europe with Machine Learning, OXFORD-Journal of Financial Econometrics, 2023, Vol.-21, No.-2, Pp-569–596. https://doi.org/10.1093/jjfinec/nbab010
  5. Mona Aly SharafEldin1, Amira M. Idrees and Shimaa Ouf (2025), A Proposed Framework for Loan Default Prediction Using Machine Learning Techniques, International Journal of Advanced Computer Science and Applications, vol.-16, no. 6, Pp-412-425, 2025
  6. Herui Chen (2022), Prediction and Analysis of Financial Default Loan Behaviour Based on Machine Learning Model, Hindawi- Computational Intelligence and Neuroscience, vol-2022, Article ID 7907210, Pp-1-10, https://doi.org/10.1155/2022/7907210
  7. Leticia Monje1, Ramón Alberto Carrasco and Manuel Sánchez Montañés (2025), Machine Learning XAI for Early Loan Default Prediction, Computational Economics, Springer, https://doi.org/10.1007/s10614-025-10962-9
  8. kinjole, A., Shobayo, O., Popoola, J., Okoyeigbo, O. and Ogunleye, B. (2024) Ensemble-Based Machine Learning Algorithm for Loan Default Risk Prediction, MDPI- Mathematics 2024, vol-12, 3423. https://doi.org/10.3390/ math1221342
  9. S. Saini, A. Bhatnagar, and L. Rani (2023), Loan approval prediction using machine learning: A comparative analysis of classification algorithms, in 2023 3rd Int. Conf. Adv. Comput. Innov. Technol. Eng. (ICACITE), May 2 023, pp. 1821-1826.
  10. Jovanne C. Alejandrino1, Jovito Jr. P. Bolacoy1 and John Vianne B. Murcia (2023), Supervised and unsupervised data mining approaches in loan default prediction, International Journal of Electrical and Computer Engineering (IJECE), April 2023, Vol.-13, Pp.-1837-1847.
  11. https: //www.kaggle.com/datasets/taweilo/loan approval-classification-data,

Download Full Paper

Download PDF No. of Downloads:2 | No. of Views: 8