• Krushan Gangurde
• Karthik Sridhar
• Sharanya Manoharan
• Muskan Markam
• Rohan Mishra

The act of borrowing money from banks has become increasingly common in modern times, as banks' primary business is lending. Their profits stem mainly from the interest on loans, but the success or failure of a bank's endeavors is largely dependent on its ability to manage credit, ensuring that borrowers repay their loans rather than default. Consequently, predicting loan defaults has become a critical concern for banks, and as such, a topic of significant research interest. Previous studies have demonstrated numerous methods for managing loan defaults, but accurate prediction is essential for maximizing profits. To this end, predictive analysis, particularly through machine learning, has emerged as a necessary modeling technique for banking. Furthermore, we suggest a recommendation system that anticipates why a loan might be declined and provides advice on how to become financially literate to increase one's chances of being approved. Machine learning models such as K-Nearest Neighbors, Gaussian Naive Bayes, Logistic Regression, XGboost, Random Forest, and SVM are used to predict the likelihood of loan repayment. The system outputs a binary prediction of whether or not the customer will repay, aiming to promote financial literacy, expedite the credit approval process, and reduce non-performing assets (NPAs) for banks

Machine learning models, Prediction, XGBoost, Random Forest, Recommendation system.

"CRED CARE - PREDICTION OF CREDIT COMPLIANCE USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 7, page no.h733-h740, July-2023, Available :http://www.jetir.org/papers/JETIR2307788.pdf

"CRED CARE - PREDICTION OF CREDIT COMPLIANCE USING MACHINE LEARNING", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 7, page no. pph733-h740, July-2023, Available at : http://www.jetir.org/papers/JETIR2307788.pdf