Prediction of food commodity prices in Indonesia based on the vector error correction model approach

This research seeks to examine the pricing dynamics and forecast the costs of three key food items in Indonesia—rice, chicken meat, and cooking oil—by employing the Vector Error Correction Model (VECM). The analysis leverages weekly price data spanning from the first week of January 2021 to the third week of September 2023. The findings reveal distinct price characteristics for each of the three commodities. The VECM model effectively captured both the long-term and short-term interrelationships among the prices of these essential food items. Based on the VECM estimation results, it was found that the prices of chicken meat and cooking oil significantly affect the price of rice in the long run. In the short run, the variance of changes in rice prices is influenced by itself, while the variance of changes in chicken meat and cooking oil prices from the beginning of the period up to the 10th period is influenced by the prices of other variables studied, but the effect is not strong enough. Because the variance decomposition value itself is always above 80%. The results of price predictions using the VECM model show a high level of accuracy, with Mean Absolute Percentage Error (MAPE) values of 0.267% for rice, 0.738% for chicken meat, and 0.857% for cooking oil, respectively. The results of this study can provide valuable information for stakeholders such as the government, producers, traders, and consumers in making better decisions related to the production, distribution, and consumption of strategic food commodities.