Abstract
We propose an intelligent approach to gasoline price forecasting as an alternative to the statistical and econometric approaches typically applied in the literature. The linear nature of the statistics and Econometrics models assume normal distribution for input data which makes it unsuitable for forecasting nonlinear, and volatile gasoline price. Karhunen-Loève Transform and Network for Vector Quantization (KLNVQ) is proposed to build a model for the forecasting of gasoline prices. Experimental findings indicated that the proposed KLNVQ outperforms Autoregressive Integrated Moving Average, multiple linear regression, and vector autoregression model. The KLNVQ model constitutes an alternative to the forecasting of gasoline prices and the method has added to methods propose in the literature. Accurate forecasting of gasoline price has implication for the formulation of policies that can help deviate from the hardship of gasoline shortage.
Chapter PDF
Similar content being viewed by others
References
Hamilton, J.D.: Historical oil shocks. In: Handbook of Major Events in Economic History (2011) (forthcoming)
Anderson, S.R., Kellogg, R., Sallee, J.M., Curtin, R.T.: Forecasting Gasoline Prices Using Consumer Surveys. Am. Econ. Rev. 101(3), 110–114 (2011)
Deltas, G.: Retail gasoline price dynamics and local market power. J. Ind. Econ. 56(3), 613–628 (2008)
Borenstein, S., Cameron, C.A., Gilbert, R.: Do gasoline prices respond asymmetrically to crude oil price change? Q. J. Econ. 102, 305–339 (1997)
Chinn, M., LeBlanc, M., Coibion, O.: The predictive of energy futures: An update on petroleum, natural gas, heating oil and gasoline. National Bureau of Economics research, Massachusetts, Cambridge, working paper 11033 (2005)
Bahrammirzaee, A.A.: comparative survey of artificial intelligence applications in finance: artificial neural networks, expert system and hybrid intelligent systems. Neural Comput. Appl. 19, 1165–1195 (2010)
Jolliffe, I.T.: Principal component analysis, 2nd edn. Springer, New York (2002)
Karhunen, J.: Robust PCA methods for complete and missing data. Neural Netw. World 5, 357–392 (2011)
Martinetz, T.M., Berkovich, S.G., Klaus, J., Schulten, K.J.: “Neural-Gas” Network for Vector Quantization and its Application to Time-Series Prediction. IEEE T. Neural Networ. 4(4), 558–569 (1993)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 IFIP International Federation for Information Processing
About this paper
Cite this paper
Chiroma, H., Abdulkareem, S., Abubakar, A.I., Sari, E.N., Herawan, T. (2014). A Novel Approach to Gasoline Price Forecasting Based on Karhunen-Loève Transform and Network for Vector Quantization with Voronoid Polyhedral. In: Linawati, Mahendra, M.S., Neuhold, E.J., Tjoa, A.M., You, I. (eds) Information and Communication Technology. ICT-EurAsia 2014. Lecture Notes in Computer Science, vol 8407. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-55032-4_25
Download citation
DOI: https://doi.org/10.1007/978-3-642-55032-4_25
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-55031-7
Online ISBN: 978-3-642-55032-4
eBook Packages: Computer ScienceComputer Science (R0)