Modeling the Probability of Bank Loan Eligibility Using Machine Learning Model

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.