Forecasting the changes of crude oil price by using fuzzy inference system / Nur Fatehah Hanum Shuhaimi, Alia Sy Afiqah Badrul Hisham and Siti Sarah Azalan

• Main Authors: Shuhaimi, Nur Fatehah Hanum, Hisham, Alia Sy Afiqah Badrul, Azalan, Siti Sarah
• Format: Student Project
• Language: English
• Published: 2018
• Subjects: Fuzzy arithmetic; Mathematical statistics. Probabilities; Data processing; Analysis; Analytical methods used in the solution of physical problems; Fuzzy logic
• Online Access: https://ir.uitm.edu.my/id/eprint/50519/1/50519.pdf; https://ir.uitm.edu.my/id/eprint/50519/

Forecasting the changes of crude oil price is always being the crucial issue in the trade merchandise's economy. Traders always face difficulties in selecting an appropriate trading strategies because of the price fluctuations. Besides, there are still no accurate method in forecasting the changes of the crude oil price. Hence, a method is needed to predict the changes of the crude oil price. Fuzzy Inference System (FIS) is chosen in this study to forecast the short-term and long-term of changes of crude oil price where the Fuzzy-Rule based consists of collection of fuzzy IF-THEN rules. This system uses two different number ofIF-THEN rules in mapping input to output to generate the outcome and to find the accuracy of the forecasting performances by comparing the Root Mean Square Error (RMSE) of FIS with RMSE of Autoregressive Integrated Moving Average (ARIMA) and Single Exponential Smoothing (SES) models. As a result, short-term forecasting by using 12 IF-THEN rules has the higher accuracy compared forecasting by using 20 IFTHEN rules and the other forecasting models but in long-term forecasting, SES outperformed the FIS. The error obtained can be accepted in the field of forecasting the changes of crude oil price because it is presumed to be low.