A Model to Improve Effectiveness and Efficiency of Credit Decision-Making

Credit decisions are important because of the credit risk exposure of lending. When lenders offer mortgages, credit cards, or other types of loans, there is a critical risk that the borrower may not repay the loan. Similarly, if a company offers credit to a customer, there is also a risk that the customer may not pay their invoices. Therefore, it is an important step in the Credit Origination process in which the counterparty assuming a Credit Risk decides to proceed with the granting of credit in accordance with their Internal Governance. This paper, it is clearly points out that modelling non-linear relationships using Artificial Neural Networks to enhance the credit decision-making process of lending institutions by predicting the probability of default of individual borrowers as well it also provides that Introduction to Risk Based Lending by using the Naïve Bayes’ Classification Algorithm to maximize the profitability and to minimize the credit risk. Furthermore, in this paper, the author has developed a model to predict the probability of default by using an ANN and introduced a Risk Rating Scale based on qualitative data which will lead to Risk Based Lending using Naïve Bayes’ classification algorithm.