LoanAdda, an Indian fintech platform has launched LoanSwift, a credit underwriting tool for faster approval of loans. The company aims to augment financial inclusion in India, to facilitate credit requirements for those with limited banking access.
LoanSwift enables LoanAdda to analyze vast amounts of non-traditional credit data to increase loan approval rates and reduce the risk of credit decisions, particularly for thin-file and no-file borrowers like millennials. It is a machine learning platform developed specifically for credit underwriting. The platform uses an algorithm to analyze tens of thousands of data points to provide a more accurate understanding of all potential borrowers. It consists of capabilities such as data aggregation, which identifies, cleans and aggregates data from thousands of sources, regardless of format and modeling tools which help train, ensemble and productionalize machine learning models that address credit risk analysis.
According to Anshuman Mishra, Co-Founder and CEO, LoanSwift uses machine learning to process each customer’s application as a vector of factors. It then maps the corresponding factors to enhance the chances of lending to the customer. This has been operationalized in the LoanAdda app and targeted at millennials, who have no or limited credit history and numerous inaccuracies, something which is not enough to access credit worthiness. As a result, they are denied credit because they cannot be underwritten by traditional systems.
“The platform analyzes thousands of nontraditional and traditional variables to accurately score borrowers, including thin-file and no-file borrowers. It can analyze vast amounts of in-house data, such as customer interaction data, payments profile, and purchase transactions. LoanSwift can also add traditional credit information and nontraditional credit variables, such as how a customer fills out a form, how much time they spend on a site, and more,” Mishra explained.
He further added that traditional underwriting works for evaluating borrowers with a considerable credit history, but when there is limited or no data, there is no possibility of ascertaining the difference between a credit worthy and a high-risk borrower. Machine learning fills those gaps by analyzing a considerably broader set of data.
There are around 456 million Indians living without access to any formal sources of credit. The biggest problem is limited access to credit for unbanked customers and poor guidance in facilitating loans. LoanAdda aims to remove the high entry barriers to formal banking and analyze customer’s data to enable and enhance their credit worthiness.