Financial institutions have battled with handling and determining the creditworthiness of their clients in the recent past. The ever-increasing customer base makes it hard for financial institutions, especially banks to follow due process of determining if a customer qualifies for a loan or not depending on one's credit history manually. As a result, there have been delays in processing customer loans, making banks and other financial institutions inefficient. Automation of these tasks has come as a factor of necessity, to improve the speed, cost, and efficiency of processing loans. Thus, an AI web-based application that predicts the probability of borrowers’ failure to repay the loans is a handy solution for this time.
The system will auto-collect historical borrowing and repaying data for that particular borrower within the shortest time with high precision whenever an individual uploads the personal data. The prototype will apply cloud cutting-edge AI and machine learning services to analyse the borrowers' creditworthiness and apply the recommendation to achieve the following: Identifying personal information of the proposed borrower, evaluating the prerequisite information for loan approval or decline, determining the credibility, notifying the lender if any loan default history, and recommending approval or disapproval based on the history of the borrower. This application will save financial institutions stress and time, avoid losses in the lending business, reduce the loan process time, decrease the likely risks associated with loans, and save the costs of the admission department.
Professional Studies (MS)
Department, Program, or Center
Graduate Programs & Research (Dubai)
Khalil Al Hussaeni
Ali Albastaki, Ali Abdullatif, "Loan Default Prediction System" (2022). Thesis. Rochester Institute of Technology. Accessed from