<![CDATA[Abstract. Cayenne pepper is a horticultural commodity with high economic value, yet its production in Baros District, Sukabumi City tends to be unstable due to fluctuations in rainfall, temperature, humidity, and sunshine duration. This uncertainty makes it difficult for farmers and local government to plan production. This study aims to build a prediction model for cayenne pepper harvest yield based on weather factors using the Random Forest Regressor algorithm with a Knowledge Discovery in Database (KDD) approach, consisting of data selection, preprocessing, transformation, data mining, evaluation, and deployment stages. The data used are weekly harvest and weather data from the Agriculture Office and the Agricultural Extension Center (BPP) of Baros District for the 2016-2025 period. The model was evaluated using random forest and produced a Mean Absolute Error (MAE) of 13.20, a Root Mean Squared Error (RMSE) of 16.39, and a coefficient of determination (R²) of 0.91, indicating that the model can explain 91% of the actual data variation. The model was then implemented into a web-based system using the Flask framework so that it can be used directly by farmers and related institutions. The results show that Random Forest Regressor is effective for predicting cayenne pepper harvest yield and can serve as a basis for decision-making in agricultural production planning in Baros District.]]>
Copyrights © 2026
