Optimizing Bank Stability Through MSME Loan Securitization: A Predictive and Prescriptive Analytics Approach

This study aims to enhance bank stability in the context of MSME loan securitization through the application of advanced decision analytics. Utilizing predictive modelling techniques, including Random Forest, Gradient Boosting, and Neural Networks, the research identifies key financial ratios and macroeconomic indicators that influence bank stability, as measured by the Z-Score. Additionally, Particle Swarm Optimization (PSO) was employed to optimize capital and liquidity ratios, revealing optimal values of 0.20 and 0.60, respectively, for maximizing stability. The study contributes to decision analytics by integrating predictive modelling, optimization, and prescriptive methods, providing a robust framework for financial institutions to improve risk management and decision-making. The findings demonstrate the superiority of machine learning models over traditional methods and highlight the critical role of financial ratios in sustaining bank stability. Future research should extend these models to broader datasets and dynamic financial environments to further enhance their predictive power and applicability.