Parameter Optimization of the Random Forest Algorithm for Predicting Corn Yields in Toba Regency
Tegar Arifin Prasetyo, Tiurma Lumban Gaol, Rudy Chandra, Yohanssen Pratama, Herlina Nikita Purba, A Manik, Olyvia Siahaan · 2024
Maize (Zea mays L.) is one of the important agricultural commodities in Indonesia. Maize crop processing is widely managed by farmers in North Sumatra, particularly in Toba Regency. However, Indonesia has not been able to meet the demand for corn production from 2009 to 2021, so there is an urgent need to increase production to avoid dependence on imports. In this research, a website is developed to predict corn yield using Random Forest algorithm. This website aims to help farmers and related parties in planning corn production better, utilizing historical data that includes data on seeds, fertilizers, land area, medicines, and crop yields from 2010 to 2023. Based on the implementation of the algorithm used and the parameter values obtained, this website is able to predict corn yields with a Mean Absolute Percentage Error (MAPE) value of 9.04%, which falls into the excellent category. The results of this study indicate that the Random Forest algorithm can be relied upon to predict corn yields in Toba Regency, so that it can help improve efficiency and effectiveness in the agricultural sector.