Credit Risk Identification and Prevention Strategies of Small and Medium-sized Banks Based on Big Data Technology

The topic of this analysis is the application of big data technology to improve credit risk identification and prevention measures in SME banks. T¬he research, it highlights credit risk’s crucial role in banking and underscores the problems smaller banks encounter when dealing with this risk due to limited resources and less evolved tools. An extensive review is conducted, showing the progression of credit risk management and big data integration into financial risk management. It discusses the revolutionary aspect of big data in credit risk analysis as well as its practical applications in small and medium-sized banks. The secondary data from Kaggle datasets are used within a quantitative research approach. Regression analysis and hypothesis testing are some of the statistical tools used in EViews to uncover patterns and correlations related to credit risk. The study determines essential factors that affect credit risk, such as borrower credit score, loan amount, interest rate, and employment. It assesses the effectiveness of big data analytics in forecasting and mitigating this risk, focusing on accuracy and model resilience. This implies that the findings show that the borrowers have a moderate level of credit risk, and the traditional financial metrics have minimal influence on the Big Data risk score predictions, which require advanced analytical approaches. Big data technology can take more than traditional credit scoring, giving small and medium-sized banks a more advanced credit risk perspective. Limitations of the research include using a simulated dataset and the range of the analysed variables. Real-world data and variables should be used in future research studies.