With the increasing needs of people, the demand for bank loans also rises. Each day, banks receive numerous loan applications from various customers and individuals, however, not all applicants are approved. Banks typically assess an applicant's eligibility before processing a loan application, a process that can be time-consuming and complex. In evaluating loan applications and making credit decisions, banks often rely on their credit scoring and risk assessment systems. Nevertheless, there are still cases where some applicants default on their payments annually, resulting in significant financial losses for financial institutions. In this research, we utilized machine learning algorithms to analyze a dataset of approved loans and predict which applicants are most deserving of a loan. The study incorporates customers' historical data, including factors such as age, income type, loan annuity, last credit bureau report, organization type, and length of employment. Various machine learning methods like Random Forest, XGBoost, Adaboost, Lightgbm, Decision tree, and K-Nearest Neighbor were utilized to identify the most influential features that impact prediction outcomes. These algorithms were then compared using standard metrics, with Logistic Regression achieving the highest accuracy rate of 92%. Key Words: Bank Loans, Logistic Regression, Credit Report, Risk Assessment