<![CDATA[Abstract In this paper, we present a comprehensive performance evaluation of the ARIMA (AutoRegressive Integrated Moving Average) model in forecasting rice production across Sumatera, Indonesia. Rice is a crucial staple crop, feeding more than half of the global population. In Sumatera, rice plays a vital role in food security, yet its cultivation is highly dependent on specific environmental conditions such as temperature, humidity, and rainfall. This study leverages historical time-series data from the years 2000 to 2020, collected from eight key provinces: Aceh, North Sumatera, West Sumatera, South Sumatera, Riau, Jambi, Bengkulu, and Lampung. The objective is to forecast rice production for the years 2021-2024 using the ARIMA method. Through rigorous model selection and evaluation, ARIMA (3,0,2) was identified as the most suitable model, providing accurate forecasts with a Mean Squared Error (MSE) of 0.0325 and a Mean Absolute Error (MAE) of 0.1445. These low error rates demonstrate the model’s capacity to capture the inherent fluctuations in rice production trends across Sumatera. The findings offer critical insights for future rice production trends and can guide policy-makers in formulating effective food security strategies. This research contributes significantly to the understanding of rice production dynamics and the application of ARIMA models in agricultural forecasting. Keywords: Rice production; Mean Squared Error; Mean Absolute Error; ARIMA; Sumatera.]]>
