Price Prediction of Vegetable Oil Kaggle Data with Multiple Linear Regression and Backpropagation

Abstract

Indonesia has an abundant agricultural sector. The agricultural sector is very abundant, one of which is coconut oil, palm oil. Oil prices are often uncontrolled fluctuations that cannot be determined based on parameters. The ups and downs of oil prices can be seen clearly from graphs and tables of previous data. Farmers who plant coconut and oil palm often experience losses due to the high cost of planting, but when harvesting the price drops. In order to reduce the losses experienced by farmers, we propose a vegetable oil price prediction system. The aim of this research is to predict the price of vegetable oil, starting from palm oil, coconut oil, fish oil, soybean oil, peanut oil, and sunflower oil by using multiple linear regression and Backpropagation methods. The data used is from Kaggle, with year and month input variables, from 2006 to 2018. The total dataset is 153 lines, used training 110 lines, and testing 43 lines. The results of our prediction of accuracy testing with MAPE, the average accuracy value of the multiple linear regression method is 0.385, and the average accuracy value of the Backpropagation method is 0.209. Based on the MAPE accuracy results, the multiple linear regression algorithm and Backpropagation show the best Backpropagation