Sovereign debt dynamics remain at the core of global financial stability, particularly in periods marked by shifting macroeconomic regimes and asymmetric global threats. Traditional econometric models have offered partial insights into debt sustainability; however, their linear assumptions often fail to capture the complexity of modern financial environments. The rise of exogenous shocks from geopolitical tensions to pandemic-driven recessions has intensified the volatility of sovereign debt markets, underscoring the need for advanced, adaptive forecasting frameworks. Against this backdrop, stochastic extensions of autoregressive integrated moving average (ARIMA) models present a robust methodological alternative. By integrating stochastic volatility and regime-switching mechanisms, these models address nonlinearities and structural breaks that characterize sovereign borrowing conditions in both developed and emerging economies. This study explores the application of stochastic ARIMA approaches to forecasting sovereign debt risks, highlighting their capacity to capture contagion effects, regime-dependent debt behaviors, and interactions with global financial threats. The framework is designed to assess how debt trajectories evolve under neutral, expansionary, and contractionary macroeconomic regimes, while accounting for asymmetries induced by trade disruptions, interest rate shocks, and capital flow reversals. Through comparative simulations, the analysis demonstrates how stochastic ARIMA not only enhances forecast accuracy but also provides policymakers with scenario-based insights into debt sustainability under uncertainty. The findings suggest that stochastic ARIMA models can serve as decision-support tools for debt managers, central banks, and international financial institutions. They bridge the gap between theoretical asset-pricing constructs and real-world risk management, offering a practical pathway to anticipate vulnerabilities before they escalate into systemic crises.