Forecasting of Rice Production Using a Linear Regression and Polynomial Regression

Rice is a staple food for most Indonesians. The growing population, which has already reached 278 million, is expected to lead to increased rice consumption. Therefore, it is important to have a system that can forecast rice production. Time series data can be used to forecast rice production. Two common time series forecasting methods are linear regression and polynomial regression. Linear regression is used for data that is linear, while polynomial regression is used for data that is non-linear. In this study, we evaluated the performance of linear regression and polynomial regression for rice production forecasting in West Nusa Tenggara Province from 2001 to 2022. The results showed that the polynomial regression model with 4-degree gave better results than the linear regression model. The RMSE and MAE for the polynomial regression model were 0.48 and 2.34, respectively, while those for the linear regression model were 0.97 and 0.87, respectively. The results of this study suggest that the polynomial regression model with 4-degree is a better choice for rice production forecasting in West Nusa Tenggara Province