Crude Oil Price Forecasting Using Long Short-Term Memory and Support Vector Regression

Abstract

Crude oil or petroleum is a non-renewable energy source derived from organic materials whose formation process is lengthy. Crude oil is a commodity whose prices often fluctuate. When there is a fluctuation, a nation's economy will be affected. The crude oil price datasets are categorized as non-linear. This research used two models to compare the performance of those two models to find the best model to predict Brent crude oil prices. The models used in this research are Long Short-Term Memory (LSTM) and Support Vector Regression (SVR). Those two methods are widely used for a similar case, such as forecasting the stock price. The dataset used in this study is the price of Brent crude oil from May 1987 to May 2022. The result of this study indicates that the deep learning algorithm, LSTM, performs better in forecasting the price of Brent crude oil with a root mean squared error value of 1.543. Index Terms—Crude Oil, Long Short-Term Memory (LSTM), Support Vector Regression (SVR), Deep Learning, Forecasting.