As people’s demands grow, so does the need for bank loans. Every day, banks receive numerous loan applications from customers and other individuals, but not every applicant is approved. Typically, banks process loan applications after verifying and evaluating the applicant’s eligibility, which is a time-consuming and challenging process. To assess loan applications and make credit approval decisions, most banks use credit scores and risk assessment systems. Despite this, some applicants still fail to repay their loans each year, leading to significant financial losses for institutions.In this study, machine learning (ML) algorithms are employed to analyze a common loan-approved dataset and predict deserving loan applicants. The dataset includes customers’ previous data such as age, income type, loan annuity, last credit bureau report, type of organization they work for, and length of employment. ML methods such as Random Forest, XGBoost, AdaBoost, LightGBM, Decision Tree, and K-Nearest Neighbors were used to identify the most relevant features-those with the greatest impact on the prediction output. These algorithms were compared and assessed using standard metrics. Among them, Logistic Regression achieved the highest accuracy at 92% and was determined to be the best model. It performed significantly better than the other ML methods in terms of the F1-Score, which was 96%.