Oil price forecasting using gene expression programming and artificial neural networks
2nd International Conference on Big Data Analysis and Data Mining
November 30-December 01, 2015 San Antonio, USA

Mohamed M Mostafa

Gulf University for Science and Technology, Kuwait

Scientific Tracks Abstracts: J Data Mining In Genomics & Proteomics

Abstract:

Crude oil plays an increasingly important role in world economy. As crude oil price series are generally considered nonlinear and non-stationary time series, which is interactively affected by many factors, predicting crude oil price accurately is rather challenging. This study aims to forecast daily oil prices using a long time series spanning the period from January 2, 1986 to June 12, 2012. We applied evolutionary techniques such as gene expression programming (GEP) and artificial neural network (NN) models to predict oil prices. Autoregressive integrated moving average (ARIMA) models are employed to benchmark evolutionary models. The results reveal that the GEP technique outperforms traditional statistical techniques in predicting oil prices. The GEP model perfectly predicts oil price in the study period. In addition, the GEP model outperforms the NN and the ARIMA models in terms of several performance statistics such as the mean squared error, the root mean squared error, and the mean absolute error. Finally, the GEP model also has the highest explanatory power as measured by the R-squared statistic. The results of this study have several important implications for both theory and practice.

Biography :

Mohamed M Mostafa has received a PhD in Business from the University of Manchester, UK. He has also earned an MS in Applied Statistics from the University of Northern Colorado, USA, an MA in Social Science Data Analysis from Essex University, UK, an MSc in Functional Neuroimaging from Brunel University, UK, an MBA and a BSc at Port Said University, Egypt. He has published over 60 research papers in several leading academic peer reviewed journals. .

Email: moustafa.m@gust.edu.kw