SUSTAINABLE DEVELOPMENT AND ECONOMIC STABILIZATION THROUGH ARTIFICIAL INTELLIGENCE IN DECISION SUPPORT SYSTEMS, FOR BUSINESS BANKRUPTCY PREDICTION

Abstract

Financial institutions, investors, and economic stability are all seriously threatened by corporate bankruptcy. Conventional models for predicting bankruptcy, like logistic regression and Altman's Z-score, frequently fall short in identifying intricate financial trends and producing precise projections. In order to improve businesses' and financial institutions' capacity to recognize bankruptcy risks in real time, this study suggests integrating artificial intelligence (AI) into decision support systems (DSS). To create a reliable bankruptcy prediction model, we examine and contrast cutting-edge machine learning methods in this study, such as Random Forest, XGBoost, and Long Short-Term Memory (LSTM) Neural Networks. To find important financial indicators that help predict bankruptcy, financial data from different businesses is processed and examined utilizing feature engineering and big data analytics. With an overall accuracy of above 90%, the tested models' performance is assessed using Precision, Recall, and F1-score. The results show that AI-powered DSS can help investors, auditors, and financial management make data-driven choices while lowering financial risks. Furthermore, by regularly examining financial accounts and recommending preventive actions for high-risk businesses, the proposed DSS offers an early warning system. By showing how AI can transform bankruptcy prediction and provide significant advantages in risk management and market stability, this study advances the nexus between finance and technology.