Forecasting Basic Commodity Prices in East Java Using a Hybrid ARIMA–LSTM Method

Abstract

Price instability and fluctuations of basic commodities in East Java pose significant challenges that affect household purchasing power and complicate regional inflation control. This study aims to develop and evaluate a forecasting model for selected food commodity prices using a decomposition-based Hybrid ARIMA–LSTM framework. Daily time-series data from 2015–2024 are decomposed into trend, seasonal, and residual components. The linear trend component is modeled using ARIMA, while separate Long Short-Term Memory (LSTM) networks are employed to model the seasonal and residual components over a 30-day forecasting horizon. The framework is evaluated using medium rice, bulk cooking oil, and purebred chicken eggs across Surabaya City, Madiun City, and Banyuwangi Regency. Experimental results indicate that the decomposition-based parallel architecture improves short-term forecasting performance compared with standalone models by reducing error accumulation between linear and non-linear components. Quantitatively, ARIMA consistently achieves a coefficient of determination (R²) above 0.96 when modeling trend components, while LSTM effectively captures seasonal patterns. However, residual-component forecasting exhibits substantially lower performance in several datasets, reflecting the difficulty of modeling irregular stochastic variations using a purely time-series approach. Overall, the proposed framework demonstrates the potential of decomposition-based hybrid forecasting for selected regional food commodity prices and provides a foundation for future forecasting-oriented decision-support applications.