An Approach to Predict Loan Eligibility using Machine Learning

Banks make the majority of their income through lending. It takes time for both the housing finance firm and the consumer who applies for the loan the procedure of getting a home loan and determining eligibility. The completion of the full process takes a lot of time. Even filling out an internet application is difficult because so many facts are needed, including the applicant's gender, marital status., education level, dependents, whether or not they are self-employed, loan amount, loan term, credit history, property area, and loan status. The target data is the loan status, while other data serve as its parameters to produce some output and reveal patterns. The business also gathers data on the urban, semi-urban, and rural areas where customers are interested in purchasing real estate. To deal with this issue Machine learning is very useful for automating the process of determining a customer's validity, but the basic problems that have been around for a while don't care about outliers or machine learning models, which reduces accuracy and degrades the model's efficiency as a result. Even though many people are looking for loans. Finding a legitimate applicant who will return the loan is difficult. Choosing a real applicant may be difficult if the process is done manually. We are establishing a machine attempting to learn loan prediction system as a result, that will determine the suitable candidates on its own. Both the applicant and the bank staff will benefit from this. The loan sanctioning period will be drastically shortened. In this study, we use the machine learning techniques of logistic regression, decision trees, and random forest to predict the loan data.