IMPROVING CREDIT SCORING MODELS THROUGH BUSINESS ANALYTICS AND CYBERCRIME PREVENTION IN FINANCIAL SYSTEMS

Abstract

Credit scoring models are very important in financial decision-making. They influence credit approvals for individuals and businesses. However, in the United States of America (U.S), traditional credit scoring systems, like FICO, are widely used. The credit system is increasingly challenged by rising cybercrime. Cybercriminal activities, such as identity theft, synthetic identity fraud, and account takeovers, can distort an individual’s credit score and compromise financial institutions. This paper explores the enhancement of U.S. credit scoring models by integrating business analytics and cybersecurity (Chen et al., 2012). Financial institutions can leverage business analytics by using data analysis, statistical models, and other quantitative methods to solve this problem. Machine learning and cybersecurity measures can also help financial institutions identify fraudulent behaviors early (Kshetri, 2017). This study demonstrates how improved credit scoring models can reduce fraudulent loan applications and improve lending decisions, safeguarding the financial system against cybercrime and fraudulent practices (Chen et al., 2012).