Rahmat Hidayat, Ansari Saleh Ahmar, Alde Alanda, Erianda Aldo, Hilda Amnur, Rasyidah
This research develops an early warning system for inflation risks by constructing a hybrid forecasting framework that integrates Triple Exponential Smoothing with GARCH models. Using monthly inflation data from Indonesia (January 2010 to September 2023), we address the critical need for proactive risk identification in monetary policy management. The hybrid approach leverages Triple Exponential Smoothing to capture trend and seasonal patterns while incorporating GARCH models to account for volatility clustering in inflation data. Results demonstrate that the hybrid model outperforms standalone models with a 27.8% reduction in forecast error and enhanced variance prediction. Most significantly, the framework enables policymakers to identify emerging inflation risks 2-3 months earlier than traditional methods, thereby expanding the window for calibrated policy responses. The Value-at-Risk estimates from the hybrid model achieve 94.5% coverage rate with narrower prediction intervals than conventional methods. Counterfactual policy analysis confirms that implementation of this framework would have enabled more timely intervention during key inflation episodes. This research contributes to risk sciences by establishing an integrated approach for inflation risk assessment that bridges statistical forecasting techniques with practical monetary policy applications. © 2026 IEEE.
Politeknik Negeri Padang, Information Technology Department, Padang, Indonesia; Universitas Negeri Makassar, Faculty of Mathematics and Natural Sciences, Department of Statistics, Makassar, Indonesia
