Perbandingan Volatilitas dan Peramalan Harga Cabai di Provinsi Bengkulu dan Tingkat Nasional

Abstract

Chili peppers are among Indonesia’s strategic horticultural commodities, with highly volatile prices that frequently contribute to food inflation, particularly at the regional level. However, previous studies have generally focused either on price volatility or forecasting separately, while comparative evidence between provincial and national markets remains limited. This study analyzes chili price volatility and evaluates the performance of a simple forecasting approach in Bengkulu Province relative to national price dynamics. Monthly price data from January 2021 to December 2025 for four major chili commodities: green cayenne chili, red cayenne chili, large red chili, and curly red chili were obtained from the National Strategic Food Price Information Center (PIHPS). Volatility was measured using the Coefficient of Variation (CV), while forecasting was conducted using Moving Average (MA) models of order 2 to 6. Model performance was evaluated using Mean Absolute Deviation (MAD), Mean Squared Error (MSE), and Mean Absolute Percentage Error (MAPE). The results show that chili prices in Bengkulu Province were more volatile than at the national level. CV values in Bengkulu ranged from 37.30% to 43.72%, indicating very high volatility, whereas national CV values ranged from 25.68% to 26.64%, classified as high volatility. The MA(2) model generally produced the best forecasting performance, with lower error values at the national level than in Bengkulu Province. These findings suggest that Moving Average performs better under relatively lower volatility conditions but is less responsive in highly volatile markets. Therefore, regional supply stabilization and more adaptive forecasting models should be considered to support future food price control policies.

Keywords

• Bengkulu Province
• chili prices
• forecasting
• moving average
• price volatility