• Gorikapudi Manidheer Babu
• Pakkela Divya Prasanna Bharathi
• Mohammad Nousheen Tabassum
• Edara Navya Chowdary
• Puli Rekha

Borrowing from financial institutions is widespread in today's culture. Every day, many people apply for loans for different reasons. However, not all candidates are reliable or accepted. A major portion of bank loans Each year, many deposits are not refunded, causing the bank to incur massive losses. Making the choice to Approve a loan carries major risks. Therefore, the purpose of this endeavor is to gather credit. Data from a range of sources are then extracted using various machine learning approaches. Important information. Using this concept, firms can determine whether to approve or Reject consumer loan proposals. This article analyses actual bank credit data and performs numerous. Loans are a major source of revenue for every bank, therefore they work relentlessly to ensure that they only lend to customers who will not default on their monthly payments. They pay close attention to this issue and utilize a variety of methods to detect and forecast their consumers' default habits. However, due to human mistake, they may miss out on important information. This work presents a better strategy to predicting defaulters based on machine learning techniques such as KNN, decision trees, SVM, and logistic regression. The accuracy of these approaches will be evaluated using metrics such as log loss, Jaccard similarity coefficient, and F1 Score. These parameters are compared to measure the accuracy of predictions.

"Developing a loan Default prediction System Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 11, page no.489-498, November-2024, Available :http://www.jetir.org/papers/JETIRGO06052.pdf

"Developing a loan Default prediction System Using Machine Learning", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 11, page no. pp489-498, November-2024, Available at : http://www.jetir.org/papers/JETIRGO06052.pdf