Open AccessCredit Risk Assessment of Loan Defaulters in Commercial Banks Using Voting Classifier Ensemble Learner Machine Learning Model
Author(s) -
Shrikant Kokate,
Manna Sheela Rani Chetty
Publication year - 2021
Publication title -
international journal of safety and security engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.202
H-Index - 10
eISSN - 2041-904X
pISSN - 2041-9031
DOI - 10.18280/ijsse.110508
Subject(s) - loan , gradient boosting , random forest , computer science , decision tree , machine learning , feature selection , credit risk , artificial intelligence , classifier (uml) , ensemble learning , finance , business
In banking sector credit score plays a very important factor. It is important to find which customer is valid and which is not valid for loan. Now to classify customer’s credit score is used. Based on this credit score of customers the bank will decide whether to approve loan or not. In banks there are major failures due to credit risks. We can automate this by using various Machine learning algorithms to identify loan defaulters. To classify and predict the customers here various Machine learning techniques like gradient boosting, random forest and Feature Selection technique along with Decision Tree are used. Using these algorithms we accurately classify valid and invalid customers for loan. Designed model can classify their customers into good and bad applicants and train the model for getting the better accuracy of the customer data.