Forecasting of carbon emissions prices by the adaptive neuro–fuzzy inference system

G. Atsalakis and D. Frantzis and C. Zopounidis

Journal of Energy Markets

Abstract: Abstract The need for accurate forecasts has increased in recent years but there has as yet been limited research on carbon emissions price trends. This study uses the adaptive neuro-fuzzy inference system (ANFIS) model to forecast the price trends of carbon emissions: ANFIS is a hybrid system consisting of neural networks and fuzzy logic. It uses a combination of the least-squares method and the back-propagation gradient descent method to estimate the optimal carbon price forecast parameters. Although the system is well known, it has been modified in order to best process the carbon emissions data sets. We used daily data sets covering the period from October 14, 2009 to October 29, 2013, using 1074 observations to train and evaluate the model. The results of the simulation and experimental investigations carried out in the laboratory showed that the model is suitable for forecasting carbon emissions price trends. A further evaluation compared the returns from trading actions, according to the signal of the forecasted system, with the buy-and-hold strategy.

References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.risk.net/journal-of-energy-markets/242 ... zzy-inference-system (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rsk:journ2:2421370

Access Statistics for this article

More articles in Journal of Energy Markets from Journal of Energy Markets
Bibliographic data for series maintained by Thomas Paine ().