PREDIKSI HARGA MINYAK KELAPA SAWIT MENTAH (CRUDE PALM OIL) MENGGUNAKAN METODE DECISION TREE

CRUDE PALM OIL PRICE PREDICTION USING DECISION TREE METHOD

Abstract

Crude palm oil (CPO) is one of Indonesia's main export commodities that has high economic value, but its price is very volatile due to various factors such as global market conditions, climate, and political policies. This research aims to build a CPO price prediction model using the Classification and Regression Tree (CART) algorithm, a form of Decision Tree method known for its ease of interpretation and high accuracy. The data used is historical CPO price data obtained from the Investing.com website within the last 10 years. In the process, the data is divided into training and testing data. The model is evaluated using metrics such as MAE (Mean Absolute Error), RMSE (Root Mean Square Error), and R² (R-Square). The results showed that the Decision Tree method with the CART algorithm was able to provide an accuracy of 93.101%, with an R² value of 0.937, RMSE of 0.062, and MAE of 0.046. This proves that the CART algorithm is suitable for predicting CPO prices and can be a decision-making tool for industry players.