ResearchBib Share Your Research, Maximize Your Social Impacts
Sign for Notice Everyday Sign up >> Login


Journal: MATTER: International Journal of Science and Technology (Vol.5, No. 2)

Publication Date:

Authors : ; ;

Page : 213-228

Keywords : Forecasting; LSTM; Moving Average; Linear Regression; ARIMA;

Source : Downloadexternal Find it from : Google Scholarexternal


Crude oil plays a big role in determining the world economy today. The increase in the oil price leads to an increase in inflation and hence reduces economic growth. More to that from crude oil, different products reduce. Therefore, a change in oil prices will directly affect these products. Because of this, it is very important to determine the future price of crude oil for better economy budgeting and future planning. Knowing the future price of oil is very challenging. Investors, business people, and the government need accurate prediction models for their decision-making. The main challenge of predicting the price of crude oil is the instability of the price of crude oil. In this paper, the study will use the deep learning techniques to capture the behavior of the crude oil price with a comparison with the other three techniques. The study will use Long Short Term Memory (LSTM) with a comparison with the Moving average (MA), linear regression (LR) and Autoregressive integrated moving average (ARIMA). Using the data from West Texas Index Intermediate (WTI), and measurement performance RMSE and R-Square, this research has proved that deep learning model (LSTM) is the best in capturing nonlinear data for the aim of predicting the future price of crude oil price.

Last modified: 2019-10-19 17:45:03