Prediction of Rubber Crop Production in Malaysia Using Machine Learning

Agriculture is a cornerstone of economic growth in many countries, especially in developing nations where it provides a significant source of employment and raw materials for industries like sugar, palm oil, and rubber. In Malaysia, agriculture is particularly vital, with rubber products being a key export. To mitigate the economic impact of potential crop shortages, a reliable prediction system for rubber production is crucial. Traditional, human-based methods for predicting crop yields are often inefficient, time-consuming, and prone to errors. For example, the crop-cut method can lead to inaccurate measurements and overestimation of production. To address these limitations, a new study introduces a machine learning-based prediction system. This system, which was developed to forecast rubber crop production in the Malaysian states of Melaka, Perak, Pahang, and Johor, utilizes several machine learning algorithms, including Random Forest, Decision Tree, Linear Regression, and Neural Network. The performance of these models was evaluated using Mean Square Error (MSE) and Mean Absolute Error (MAE). The findings of the study demonstrate that Linear Regression was the most effective algorithm, consistently providing the most accurate predictions with the lowest MAE values. This new system offers a more efficient and precise alternative to traditional methods, enabling better financial planning and decision-making for the agricultural sector.