Modeling the Probability of Bank Loan Eligibility Using Machine Learning Model

Errence Chavalala () and Lucas Thulani Khoza ()
Additional contact information
Errence Chavalala: Independent Institute of Education
Lucas Thulani Khoza: University of South Africa

A chapter in LISS 2024, 2025, pp 767-793 from Springer

Abstract: Abstract Human demands are rising because of substantial advancements in technology, and loan approval criteria in the banking sector have risen. Some characteristics were evaluated while choosing loan approval candidates to determine loan status. Banks face significant challenges when evaluating loan applications and minimizing the risks associated with the possibility of borrowers defaulting. Banks struggle with the procedure since they must thoroughly analyze each borrower’s loan eligibility. This study uses machine learning (ML) algorithms to determine the likelihood of accepting individual loan applications. This strategy can improve accuracy in selecting qualified candidates from a bank’s database. As a result, the strategy can be utilized to address the issues raised regarding the loan approval procedure. This method benefits both credit applicants and bankers by significantly reducing the turnaround times of bank loans. As the banking industry expands, an increasing number of individuals are seeking bank loans. The current study employed five alternative algorithms to estimate the accuracy of an applicant’s loan acceptance status: logistic, Naïve Bayes, K-Nearest Neighbor, Random Forest, and Decision Trees. Using these methods, the study attained a greater accuracy of 99.90% with the Random Forest algorithm, and 99.80% for the Decision Tree. These two therefore emerged as the top ML models. None of the model variables used to construct the ML models were weak or medium, indicating that they are not suitable for model development. There is a relationship between loan status, loan type, and age. Both loan type and age have a direct influence on loan status. The study found that there is no relationship between loan status and loan length. The loan term has no direct influence on loan status.

Keywords: Bank loans; training data set; testing data set; logistic; KNN; Naïve Bayes; Random Forest; Decision Tree; undersampling (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnopch:978-981-96-9697-0_59

Ordering information: This item can be ordered from
http://www.springer.com/9789819696970

DOI: 10.1007/978-981-96-9697-0_59

Access Statistics for this chapter

More chapters in Lecture Notes in Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().