--- Loan approval is an essential process in financial institutions that requires careful evaluation of an applicant’s financial background and repayment capability. Traditional loan approval methods are often manual, time-consuming, and may lead to inconsistent decisions due to human involvement. To address these challenges, this study proposes a machine learning–based system for predicting loan eligibility using applicant demographic and financial information such as income, loan amount, credit score, employment status, number of dependents, and asset values. The dataset is preprocessed using techniques including missing value handling, categorical encoding, and feature scaling to improve data quality and model performance. Multiple machine learning algorithms such as Logistic Regression, Decision Tree, Random Forest, Gradient Boosting, Support Vector Machine, and K-Nearest Neighbors are implemented and evaluated using performance metrics like accuracy, precision, recall, F1-score, and confusion matrix. Experimental results indicate that ensemble models such as Random Forest and Gradient Boosting achieve higher predictive accuracy compared to other classifiers. The best performing model is integrated into a Streamlit-based web application that enables real-time loan eligibility prediction through a user-friendly interface. The proposed system helps financial institutions automate the loan approval process, reduce manual effort, and improve decision-making efficiency.