Machine Learning Algorithms for Automation in Loan Prediction System

In banking system, distribution of loans is the core business part of almost every bank. Banks have many sources of income and schemes to sell but main source of income of any banks is on the income received by giving loans to customers. So they can earn from interest of those loans which they credit. Technology has boosted the existence of the humankind the quality of the life they live. Every day we are planning to create something innovative and also plan for future so, for this we need money. With the advancement of technology, there are so many enhancements in the banking sector also. With the enhancement in the banking sector lots of people are applying for bank loans. Many people depend on bank loans for different purpose. Risk is constantly involved in approval of loans because banking officials are very acutely aware of the price of the mortgage quantity by its customers. Even after taking lot of precautions, approval choices are not correct every time. So, there is need of automation of this system so that loan approval will become less risky and incur less loss for banks because bank has its limited assets which it has to allocate to limited and deserving people only, so finding out to whom the loan can be granted which will be a safer option for the bank is a typical process. Also, banks have to maintain their NPA( Non-Performing Asset) and CRAR( Capital to Risk Weighted Assets Ratio). So in this paper we are trying to reduce this risk factor behind selecting the right person so as to save lots of bank efforts and assets. This can be done via Machine Learning algorithms like Random Forest, Logistic Regression, Support Vector Machine, Naïve Bayes, KNN which provide higher efficiency in data classification. The main objective of this paper is to predict whether approving the loan to particular applicant will be the right choice or not using the Random Forest Algorithm.