Loan Defaulter Prediction System using Machine Learning

With the growth in banking sector lots of people and companies are applying for bank loans but the banks have their limited assets which they have to grant which will be a safer option for the banks is a difficult process. So, in this paper we try to reduce these risk factor/s of the banks to select a particular person or a company for providing loans. This is done by analyzing the data of the previous records of the people to whom the loan was granted before and on the basis of these records/experiences the system will be trained using the machine learning model which gives the most accurate result. The main objective of this project is to predict whether assigning the loan to particular person/company will be safe or not. This will be done by finding out the chances of a loan seeker being a defaulter or not. To achieve the maximum limit of the goal, applying classification models is the most efficient way. In this particular research, the three most popular and useful models; Logistic Regression, Random Forest, Decision Tree and Support Vector Machine are being implemented. Simultaneously, users who are also the bank personnel, can also have an access to a User Interface which is discussed in this paper as well. The UI will allow the users to input data for new loan seekers, so that the banks can predict the output for a loan seeker being defaulter or not in the form of binary output.
Department Name
Electrical and Computer Engineering
North South University
Printed Thesis