Comparison of Linear Regression and Random Forest Algorithms for Premium Rice Price Prediction (Case Study: West Java)

Abstract

The staple food commodity that is crucial to the Indonesian society is rice. Rice often experiences fluctuations in prices. These fluctuations can be predicted using machine learning methods. The aim of this research is to evaluate the accuracy of machine learning algorithms in predicting the premium rice prices in the West Java Province, Indonesia. Two methods used in this study are Linear Regression and Random Forest. The dataset used consists of 6096 records from the Indonesian Food Commodity Management Agency. The evaluation results show that the Random Forest algorithm has an accuracy rate of 98.69%, while the Linear Regression algorithm has an accuracy rate of 95.08%. Based on these results, it is concluded that the Random Forest algorithm is more effective in predicting premium rice prices in the West Java Province compared to the Linear Regression algorithm.