Economic Scenario Generation for Forward-Looking Risk Management in Indonesia: A VAR-Based Framework Integrating Macroeconomic Dynamics and Recession Regimes

The emerging market economy is characterized by closely interconnected macroeconomic and financial risks, posing significant challenges for long-horizon risk management among insurers, pension funds, and other liability-driven investors. This paper proposes and empirically validates an integrated Economic Scenario Generator (ESG) calibrated to Indonesian data, designed to generate internally coherent forward-looking scenarios for stress testing and asset–liability management applications. The proposed framework integrates a Vector Autoregression (VAR) model to capture the joint evolution of macroeconomic variables, a logistic regression specification to estimate recession probabilities, and regime-sensitive linear asset-mapping models that link government bond yields to macroeconomic drivers while accounting for yield persistence dynamics. The models are calibrated using monthly Indonesian macroeconomic indicators and government bond yield data spanning 2014–2022, and are assessed through parameter stability diagnostics, expanding-window out-of-sample validation, and 60-month-horizon Monte Carlo simulations. The VAR module successfully preserves key dynamic interactions and historical correlation structures among macroeconomic variables, while the recession-probability specification demonstrates moderate out-of-sample discriminatory performance in an imbalanced environment. The asset-mapping equations display substantial explanatory power across maturities, with adjusted R2 values between 0.959 and 0.994, yielding economically interpretable sensitivities of bond yields to macroeconomic conditions. Simulation results generate plausible long-term trajectories for both macroeconomic indicators and yield curves, although tail risks remain understated under Gaussian innovation assumptions. Overall, the findings suggest that a transparent, modular ESG constructed from standard econometric techniques can provide a practical foundation for forward-looking risk assessment and liability-driven investment analysis in emerging markets, while underscoring the importance of stress-oriented extensions to better capture extreme market dynamics.