Article
Improving Artificial Intelligence Forecasting Models
Performance with Data Preprocessing: European Union
Allowance Prices Case Study
Miguel A. Jaramillo-Morán
1,
* , Daniel Fernández-Martínez
1
, Agustín García-García
2
and
Diego Carmona-Fernández
1
Citation: Jaramillo-Morán, M.A.;
Fernández-Martínez, D.; García-García,
A.; Carmona-Fernández, D. Improving
Artificial Intelligence Forecasting
Models Performance with Data
Preprocessing: European Union
Allowance Prices Case Study. Energies
2021, 14, 7845. https://doi.org/
10.3390/en14237845
Academic Editor: Nuno Carlos Leitão
Received: 18 October 2021
Accepted: 20 November 2021
Published: 23 November 2021
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2021 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
1
Department of Electrical Engineering, Electronics and Automation, School of Industrial Engineering,
University of Extremadura, Avda. Elvas s/n, 06006 Badajoz, Spain; danielfm@unex.es (D.F.-M.);
dcarmona@unex.es (D.C.-F.)
2
Department of Economics, Faculty of Economics and Business Sciences, University of Extremadura, Avda.
Elvas s/n, 06006 Badajoz, Spain; agarcia@unex.es
* Correspondence: miguel@unex.es; Tel.: +34-924-289-928
Abstract:
European Union Allowances (EUAs) are rights to emit CO
2
that may be sold or bought
by enterprises. They were originally created to try to reduce greenhouse gas emissions, although
they have become assets that may be used by financial intermediaries to seek for new business
opportunities. Therefore, forecasting the time evolution of their price is very important for agents
involved in their selling or buying. Neural Networks, an artificial intelligence paradigm, have been
proved to be accurate and reliable tools for time series forecasting, and have been widely used to
predict economic and energetic variables; two of them are used in this work, the Multilayer Preceptron
(MLP) and the Long Short-Term Memories (LSTM), along with another artificial intelligence algorithm
(XGBoost). They are combined with two preprocessing tools, decomposition of the time series into
its trend and fluctuation and decomposition into Intrinsic Mode Functions (IMF) by the Empirical
Mode Decomposition (EMD). The price prediction is obtained by adding those from each subseries.
These two tools are combined with the three forecasting tools to provide 20 future predictions of
EUA prices. The best results are provided by MLP-EMD, which is able to achieve a Mean Absolute
Percentage Error (MAPE) of 2.91% for the first predicted datum and 5.65% for the twentieth, with a
mean value of 4.44%.
Keywords:
European Union allowances; CO
2
price prediction; emission allowances; neural networks;
forecasting
1. Introduction
Since the European Union (EU) created the Emission Trading System (EU ETS) in
2005 to combat climate change, it has become one of the cornerstones of the European
environmental policy, with strong implications for industrial activities and repercussions
that reach all economic and social sectors. Its main goal is to reduce greenhouse gas
emission. It is supposed that companies producing carbon emissions must effectively
manage associated costs by buying or selling rights to emit CO
2
, the so-called European
Union Allowances (EUAs). The EU ETS is a cap-and-trade system, which includes only
large stationary sources of emissions belonging to the most pollutant industrial sectors of
the European economy (power plants, oil refineries, ferrous metallurgy, cement clinker or
lime, glass—including glass fiber—ceramic products by firing, and pulp, paper and board).
Companies involved can either use EUAs to compensate their emissions or sell them
to others that need them [
1
]; they are allowed to trade emission allowances freely within
the EU, so the system seeks to ensure that overall emissions are reduced, but also that cuts
are made by those companies that can achieve the most efficient abatement costs [2,3].
Energies 2021, 14, 7845. https://doi.org/10.3390/en14237845 https://www.mdpi.com/journal/energies
