Enhancing Bankruptcy Prediction: The Integration of Financial Ratios and Artificial Intelligence for more Accurate Risk Assessment

The increasing complexity and volatility of global financial markets have intensified the need for more accurate bankruptcy prediction models to mitigate financial distress and corporate failures. Traditional models, such as Altman’s Z-score and Ohlson’s O-score, rely on financial ratios to assess insolvency risk. However, these models are limited by their linear assumptions and industry-specific constraints, making them less effective in capturing nonlinear financial relationships and evolving market dynamics. This study addresses the limitations of traditional bankruptcy prediction models by integrating artificial intelligence (AI) techniques with financial ratios to enhance predictive accuracy. The research aims to (1) assess the effectiveness of traditional financial ratio models in bankruptcy prediction, and (2) evaluate the impact of AI-based models and hybrid approaches in improving bankruptcy risk assessment. A mixed-methods approach was used, analyzing financial data from 50 firms that have either declared bankruptcy or are at high risk. Statistical modeling and machine learning algorithms, including neural networks, decision trees, and random forests, were applied to compare prediction accuracy. The findings revealwed that AI-based models outperform traditional models, with accuracy rates improving from 72% (traditional models) to 87% (AI models), and up to 91% with hybrid AI-financial ratio models. Incorporating non-traditional indicators such as market sentiment, macroeconomic trends, and operational metrics further enhances predictive performance. The study concludes that a hybrid AI-financial ratio model offers the most reliable bankruptcy prediction framework, reducing misclassification risks and enabling early financial distress detection. It recommends the adoption of AI-enhanced financial analysis tools in corporate risk management to support proactive decision-making and financial stability.