SCORECARD: AN ADVANCEMENT OF CREDIT SYSTEM IN BANKING SECTOR

Abstract

The role of a country's financial institutions in economic change is critical. The capacity of a bank to handle risks such as market risk, credit risk, and liquidity risk may be used to gauge its success over time. Many rising economies, including India, are undergoing financial sector transformations, particularly in the banking sector. The banking industry may help to stabilise the financial markets by developing a sound financial system. The developed market's product choice has increased as financial rules have been reduced. Credit cards, real estate, exits, and a variety of off-balance sheet commodities are among the new goods launched. As a result of the new perspectives, additional banking resources have been developed, allowing traditional financial mediation to make bigger profits. Simultaneously, new risky regions are being opened up. The Indian banking industry has adapted to new competition, dangers, and uncertainties during the last decade. Customer failures, gap gaps, and unfavourable market movements are all potential sources of risk. A few years ago, the Indian banking industry began the process of digital transformation. While the original goal may have been to combat competition from tech-savvy, new-age competitors, the COVID-19 situation may be a game changer, forcing banks to use digital technologies. It's critical to not only deal with COVID, but also to plan for recovery after the crisis. Banks might try to develop digitally in India since both urban and rural areas have significant cell phone penetration and data availability. Because of the current conditions, both vendors and buyers are more familiar with the usage of technology. To allow digital banking for their consumers, banks might partner with technology suppliers or build their own digital solutions. Banks, NBFCs, and other lending institutions have gathered a vast quantity of data on their clients' default behaviour. The date of birth, gender, income, and job status of a borrower are examples of demographic information. Furthermore, with their credit products, agencies have collected a significant amount of business expertise. Credit risk analysis and decision-making for loan approval are two of the most important operations for financial institutions. A data-driven risk model is built that evaluates the chance of a borrower defaulting on a loan based on prior history. 6 For money lending organisations, credit scoring has evolved into a vital risk management tool. Statistical and classical machine learning models have been the most investigated risk management methods in the credit scoring literature throughout the years, but deep learning models have lately gotten a lot of attention. Despite the greater performance of deep learning models, a better understanding of how these models produce predictions is still required. Deep learning algorithms' lack of transparency has stymied their usage in credit rating. Automated choices created by non-transparent models must be explained, which is a requirement for lending institutions.