Artificial Neural Network as a universal function approximators can be used for mapping any nonlinear function. Used in different fields of application (congnitive science, engineering, biology, finance..), ANN have become popular in finance for their power in pattern recognition, classification and forecasting. This paper specifically examines the used of ANN in the energy market in order to build a forecast price on the energy commodities. A brief study on the feature of the energy market, in particular crude oil and natural gas prices, will be followed by an implementation of an ANN system for the forecast. Finally a comparison between a real and estimated price will be done to see if the ANN could be considered a good forecasting tool also in the energy market.

Forecasting energy market: an artificial neural network approach

Dario, Ugo
2015/2016

Abstract

Artificial Neural Network as a universal function approximators can be used for mapping any nonlinear function. Used in different fields of application (congnitive science, engineering, biology, finance..), ANN have become popular in finance for their power in pattern recognition, classification and forecasting. This paper specifically examines the used of ANN in the energy market in order to build a forecast price on the energy commodities. A brief study on the feature of the energy market, in particular crude oil and natural gas prices, will be followed by an implementation of an ANN system for the forecast. Finally a comparison between a real and estimated price will be done to see if the ANN could be considered a good forecasting tool also in the energy market.
2015-02-23
File in questo prodotto:
File Dimensione Formato  
835313-1153884.pdf

accesso aperto

Tipologia: Altro materiale allegato
Dimensione 1.49 MB
Formato Adobe PDF
1.49 MB Adobe PDF Visualizza/Apri

I documenti in UNITESI sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.14247/11283