<![CDATA[Finance loans play a crucial role in the global economy, supporting individuals and businesses in accessing capital for investment and financial stability. However, more than 60% of financial institutions struggle with identifying credit risks due to the limitations of traditional assessment models, which fail to capture complex borrower behavior. Additionally, 75% of financial firms have adopted AI-driven credit risk management, yet challenges remain in model validation and decision-making transparency. This study applies machine learning techniques, including Logistic Regression, Decision Tree, Random Forest, and Support Vector Machine (SVM), to enhance loan eligibility prediction. The dataset underwent preprocessing, including handling missing values, feature engineering, and data standardization. Model evaluation used accuracy, precision, recall, and F1-score. Logistic Regression achieved the highest F1-score at 88.6% and recall at 98.6%, while Random Forest recorded the highest precision at 82.3%. Feature importance analysis identified Credit History as the most influential factor, followed by Loan Amount and Total Income. While machine learning improves loan risk assessment, challenges remain in model interpretability. Future research should integrate explainable AI (XAI) and alternative credit scoring factors to enhance model transparency and robustness in real-world applications]]>
Copyrights © 2025
