A hybrid optimized artificial intelligent model to forecast crude oil using genetic algorithm

Crude oil is one of the most critical energy commodities while with coal and natural gas are projected to provide roughly the 86% share of the total US primary energy supply in 2030. In this study, a novel hybrid optimum model based on artificial intelligent (AI) is proposed for world crude oil spot price forecasting. A three-layer feed forward neural network (FNN) model was used to model the oil price forecasting. Genetic algorithm (GA) is employed not only to improve the learning algorithm, but also to reduce the complexity in parameter space. GA optimizes simultaneously, the connection weights between layers and the thresholds. In addition, GA reduces the dimension of the feature space and eliminates irrelevant factors. For verification and testing, two main crude oil price series, West Texas intermediate (WTI) crude oil spot price, Brent crude oil spot price and Iran crude oil are used to test the effectiveness of the proposed optimized neural network. Results show that optimized model has advantages in comparison with conventional ANN in terms of accuracy, variability, model creation and model examination. Both simulated and actual data sets are used for comparison.   Key word: Artificial neural network, crude oil, genetic algorithm, optimization.

[1]  Halbert White,et al.  Connectionist nonparametric regression: Multilayer feedforward networks can learn arbitrary mappings , 1990, Neural Networks.

[2]  G. C. Watkins,et al.  How volatile are crude oil prices , 1994 .

[3]  Jose Alvarez-Ramirez,et al.  Symmetry/anti-symmetry phase transitions in crude oil markets , 2003 .

[4]  John H. Holland,et al.  Adaptation in Natural and Artificial Systems: An Introductory Analysis with Applications to Biology, Control, and Artificial Intelligence , 1992 .

[5]  M. A. Kaboudan,et al.  Compumetric forecasting of crude oil prices , 2001, Proceedings of the 2001 Congress on Evolutionary Computation (IEEE Cat. No.01TH8546).

[6]  Michael Ye,et al.  Forecasting short-run crude oil price using high- and low-inventory variables , 2006 .

[7]  Bruce Abramson,et al.  Using belief networks to forecast oil prices , 1991 .

[8]  Michael Ye,et al.  Forecasting crude oil spot price using OECD petroleum inventory levels , 2002 .

[9]  Michael Ye,et al.  A monthly crude oil spot price forecasting model using relative inventories , 2005 .

[10]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[11]  S. Gurcan Gulen,et al.  Efficiency in the crude oil futures market , 1998 .

[12]  Hamid Baghestani,et al.  On the predictive accuracy of crude oil futures prices , 2004 .

[13]  Kin Keung Lai,et al.  Foreign-Exchange-Rate Forecasting with Artificial Neural Networks , 2007 .

[14]  Claudio Morana,et al.  A semiparametric approach to short-term oil price forecasting , 2001 .

[15]  Sam Mirmirani,et al.  A Comparison of VAR and Neural Networks with Genetic Algorithm in Forecasting Price of Oil , 2003, IC-AI.

[16]  R. Rossiter,et al.  Are there exploitable inefficiencies in the futures market for oil , 2007 .

[17]  K. Lai,et al.  Forecasting crude oil price with an EMD-based neural network ensemble learning paradigm , 2008 .

[18]  S. Hammoudeh,et al.  An empirical exploration of the world oil price under the target zone model , 2002 .

[19]  Bruce Abramson,et al.  Probabilistic forecasts from probabilistic models: A case study in the oil market , 1995 .

[20]  Hillard G. Huntington,et al.  Oil Price Forecasting in the 1980s: What Went Wrong?* , 1994 .

[21]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[22]  A. Lanza,et al.  Modeling and forecasting cointegrated relationships among heavy oil and product prices , 2005 .