Data Analysis of Loan Defaulters Prediction Model Using Machine Learning Techniques
DOI:
https://doi.org/10.17010/ijcs/2024/v9/i4/174567Keywords:
AOC_ROC, Machine Learning, Precision, Recall, SMOTE, Prediction model, Recommendation.Publication Chronology: Paper Submission Date: July 5, 2024, Paper sent back for Revision, July 15, Paper Acceptance Date: July 17, Paper Published Online: August 5, 2024.
Abstract
In recent times, the defaulters of loans have become a serious concern for the banking sector. To overcome this problem, the proposed prediction model has been recommended to predict the defaulters using different Machine Learning algorithms. This paper builds a loan defaulters prediction model based on real-world user loan data. The SMOTE method is adopted to cope with the problem of imbalance class in the dataset, and then a series of Machine Learning algorithms is used to find the best model; as a result, the Naive Bayes model performed better compared to other models based on the output of Recall, Precision, and AOC_ROC accuracy.
Downloads
Published
How to Cite
Issue
Section
References
[1] A. A. A. Albastaki, “Loan Default Prediction System,” Thesis, Rochester Inst. Technol., 2022. [Online]. Available: https://repository.rit.edu/cgi/viewcontent.cgi?article=12544&context=theses
[2] J. Chen, “Default: What it means, what happens when you default, and examples,” investopedia.com. [Online]. Available: https://www.investopedia.com/terms/d/default2.asp
[3] J. Lin, “Research on loan default prediction based on logistic regression, randomforest, xgboost and adaboost,” SHS Web Conferences, vol. 181, Art. no. 02008, Jan. 2024, doi: 10.1051/shsconf/202418102008.
[4] M. Alsaleem and S. Hasoon, “Predicting bank loan risks using machine learning algorithms,” AL-Rafidain, J. Comp. Sciences Math., vol. 14, no. 1, pp. 159-168, Jun. 2020. doi: 10.33899/csmj.2020.164686.
[5] A. Kacheria, N. Shivakumar, S. Sawkar, and A. Gupta, “Loan sanctioning prediction system,” Int. J. Soft Comput. Eng., vol. 6, no. 4, pp. 50-53, Sep. 2016.
[6] A. Uwais, “Loan default prediction using Spark Machine Learning algorithms,” 2021. [Online]. Available: https://ceur-ws.org/Vol-3105/paper30.pdf
[7] L. Zhu, L., D. Qiu, D. Ergu, C. Ying, and K. Liu, “A study on predicting loan default based on the random forest algorithm,” Procedia Comp. Sci., vol. 162, Jan. 2019. [Online[. Available: https://www.researchgate.net/publication/338286615_A_study_on_predicting_loan_default_based_on_the_random_forest_algorithm
[8] C. N. Kumar, D. Keerthana, M. Kavitha, and M. Kalyani, "Customer loan eligibility prediction using Machine Learning algorithms in banking sector," 2022 7th Int. Conf. Communication Electronics Syst., Coimbatore, India, 2022, pp. 1007-1012, doi: 10.1109/ICCES54183.2022.9835725.
[9] V. Singh, A. Yadav, R. Awasthi, and N. Partheeban, "Prediction of modernized loan approval system based on Machine Learning approach," 2021 Int. Conf. Intell. Technologies, Hubli, India, 2021, pp. 1-4, doi: 10.1109/CONIT51480.2021.9498475.
[10] P. N. Hegde, Deepa, C. Shetty, Rashmi N., Dhananjaya B., and Prathvakshini, "Predictive analysis of loan data using Machine Learning," 2022 Int. Conf. Artif. Intell. Data Eng., Karkala, India, 2022, pp. 272-276, doi: 10.1109/AIDE57180.2022.10060781.
[11] “What is Binning?,” 2024. [Online]. Available: https://docs.tibco.com/pub/spotfire/7.0.1/doc/html/bin/bin_what_is_binning.htm
[12] A. Sethi, “One hot encoding vs. label encoding in Machine Learning,” 2024. [Online]. Available: https://www.analyticsvidhya.com/blog/2020/03/one-hot-encoding-vs-label-encoding-using-scikit-learn/
[13] P. Tumuluru, L. R. Burra, M. Loukya, S. Bhavana, H. M. H. CSaiBaba, and N. Sunanda, "Comparative analysis of customer loan approval prediction using Machine Learning algorithms," 2022 2nd Int. Conf. Artif. Intell. Smart Energy, Coimbatore, India, pp. 349-353, 2022, doi: 10.1109/ICAIS53314.2022.9742800.
[14] L. Victor and M. Raheem, “Loan default prediction using Genetic Algorithm: A study within peer-to-peer lending communities,” Int. J. Innovative Sci. Res. Technol., vol. 6, no. 3, pp. 1195-1205, 2021. [Online]. Available: https://ijisrt.com/assets/upload/files/IJISRT21MAR687.pdf
[15] V. Kotu and B. Deshpande, Data Sci. Concepts Pract. 2nd ed., 2019. Cambridge: Morgan Kaufmann.
[16] N. Darapaneni, A. Kumar, A. Dixet, M. Suriyanarayanan, S. Srivastava, and A. R. Paduri, "Loan prediction software for financial institutions," 2022 Interdisciplinary Res. Technol. Manage., Kolkata, India, pp. 1-8, doi: 10.1109/IRTM54583.2022.9791797.
[17] D. Nautiyal, “ML|Underfitting and Overfitting.” [Online] Available: https://www.geeksforgeeks.org/underfitting-and-overfitting-in-machine-learning/
[18] J. Korstanje, “Towards Data Science.” [Online] Available: https://towardsdatascience.com/smotefdce2f605729#:~:text=SMOTE%20is%20a%20machine%20learning,with%20this%20type%20o f%20data
[19] L. Zhu, D. Qiu, D. Ergu, C. Ying, and K. Liu, “A study on predicting loan default based on the random forest algorithm,” Procedia Comp. Sci., vol. 162, pp. 503-513, 2019, doi: 10.1016/j.procs.2019.12.017.
