Authors :
S. Vishnu Priya; A. Karmehala
Volume/Issue :
Volume 9 - 2024, Issue 2 - February
Google Scholar :
https://tinyurl.com/3aesjy7z
Scribd :
https://tinyurl.com/2fu95r6u
DOI :
https://doi.org/10.5281/zenodo.10785580
Abstract :
This research study focuses on the prediction
of loan approval in a bank by utilizing logistic regression
and support vector machine (SVM) algorithms. Logistic
regression achieves an accuracy of 83.78%, while SVM
achieves an accuracy of 83%. The dataset used for
training and testing the models consists of various
features including income, credit history, employment
status, and loan amount. Both algorithms exhibit
promising performance in accurately predicting loan
approval outcomes. These findings indicate that logistic
regression and SVM can serve as effective tools for
banks to assess the probability of loan approval, thereby
assisting in their decision-making process. Further
analysis and comparison of these models can offer
valuable insights for optimizing loan approval prediction
systems in the banking industry.
Keywords :
Loan Approval, Logistic Regression, Support Vector Machine (SVM).
This research study focuses on the prediction
of loan approval in a bank by utilizing logistic regression
and support vector machine (SVM) algorithms. Logistic
regression achieves an accuracy of 83.78%, while SVM
achieves an accuracy of 83%. The dataset used for
training and testing the models consists of various
features including income, credit history, employment
status, and loan amount. Both algorithms exhibit
promising performance in accurately predicting loan
approval outcomes. These findings indicate that logistic
regression and SVM can serve as effective tools for
banks to assess the probability of loan approval, thereby
assisting in their decision-making process. Further
analysis and comparison of these models can offer
valuable insights for optimizing loan approval prediction
systems in the banking industry.
Keywords :
Loan Approval, Logistic Regression, Support Vector Machine (SVM).
