A Unique Expert System for Optimum Oil Price Estimation by Integration of Fuzzy Cognitive Map, Neural Networks and GA
1021 Words5 Pages
Crude oil plays an important role in any economies. The role of oil in the world economy becomes more and more significant, because nearly two-thirds of the world’s energy consumption comes from the crude oil and natural gas. The crude oil price is basically determined by its supply and demand and it is strongly influenced by many events like the weather, inventory, GDP growth, refinery operable capacity, political aspects and people’s expectation. Sharp oil price movements are likely to disturb aggregate economic activity and volatile oil prices have been considerable interest to many researchers and institutions. Therefore, forecasting oil prices is an important and very hard topic due to its intrinsic difficulty and practical applications.
There is an array of methods that are available today for forecasting energy price. An appropriate method is chosen based on the nature of the data available and the desired nature and level of detail of the forecasts (Azadeh et al. 2010). For crude oil price forecasting, Mirmirani and Li (2004) applied VRA and ANN techniques to make ex-post forecast of US oil price movement. Lagged oil price, lagged oil supply, and lagged energy consumption were used as three endogenous variables for VAR-based forecast. Ye et al. (2006) provided a model to forecast crude oil spot prices in the short-run using high- and low-inventory variables. They showed that the non-linear-term model better captures price responses at very high- or very low-inventory levels and improves forecasting capability. Wang et al. (2005) proposed a new integrated TEI@I methodology and showed a good performance in crude oil price forecasting with back propagation neural network (BPNN) as the integrated technique. Similarly, Shambora...
... middle of paper ...
... prices using readily available data (crude oil ending stocks, percent utilization of refinery operable capacity, oil price of a month before and oil price of two months before) is developed. In addition, this paper examines the feasibility of applying fuzzy expert system in crude oil price forecasting through the contrast with ANN, ANFIS and GA models.
The rest of the paper is organized as follows. Section 2 presents main modules of fuzzy expert system (ANN, ANFIS, and GA). Section 3 describes fuzzy cognitive map expert system for crude oil price prediction. To evaluate the fuzzy expert system, a main crude oil price series, West Texas Intermediate (WTI) crude oil spot price is used to test the effectiveness of the proposed methodology. Its comparable results with ANN, ANFIS and GA methods are presented in section 4. Some concluding remarks are made in section 5.