JOURNAL OF LIAONING TECHNICAL UNIVERSITY
(NATURAL SCIENCE EDITION)
LIAONING GONGCHENG JISHU DAXUE XUEBAO (ZIRAN KEXUE BAN)
辽宁工程技术大学学报（自然科学版）
FORECASTING INFLATION VOLATILITY IN SOUTH SULAWESI USING GJR-GARCH AND GENETIC ALGORITHM
Lili Magfirah Rahma Sudirman, Georgina Maria Tinungki*, Nirwan
Abstract-
This study aims to forecast inflation volatility in South Sulawesi Province using the GJR-GARCH model optimized by a Genetic Algorithm (GA). The GJR-GARCH model is employed to capture asymmetric effects in inflation volatility, while the GA is used to optimize parameter estimation and achieve globally optimal solutions. The results show that the GJR-GARCH model optimized with GA produces lower Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) compared to the standard GJR-GARCH model, indicating superior predictive performance. These findings suggest that integrating GJR-GARCH with GA enhances forecasting accuracy and provides a promising approach for modeling economic time series with nonlinear and heteroskedastic characteristics, which can support policymakers in monitoring and managing inflation risks.
Keywords- Inflation, Volatility, GJR-GARCH, Genetic Algorithm, Forecasting.