AI Driven Fiscal Risk Assessment in the Eurozone: A Machine Learning Approach to Public Debt Vulnerability

This study applies supervised machine learning algorithms to macro-fiscal panel data from 20 EU member states (2000–2024) to model and predict fiscal stress episodes in the Eurozone. Conventional frameworks for assessing public debt sustainability typically rely on static thresholds and linear dynamics, which are inadequate for capturing the complex, non-linear interactions inherent in fiscal datasets. To address this limitation, we implement logistic regression, random forests, and XGBoost classifiers using fiscal indicators such as debt-to-GDP ratio, primary balance, GDP growth, interest rates, and inflation. Model performance is assessed through out-of-sample validation metrics and feature importance analyses. Results indicate that machine learning models outperform traditional benchmarks in identifying periods of fiscal vulnerability, underscoring their utility for scalable early warning systems and enhanced macro-financial oversight. This work advances FinTech applications in sovereign risk monitoring by demonstrating the efficacy of AI-based tools in improving fiscal governance and policy responsiveness.