Optimizing Predictor Variables in Artificial Neural Networks When Forecasting Raw Material Prices for Energy Production

Energies

卷:13

Alicja Krzemień¹  Marta Matyjaszek²  Krzysztof Wodarski³  Gregorio Fidalgo Valverde⁴  Pedro Riesgo Fernández⁴ 

[1] Department of Risk Assessment and Industrial Safety, Central Mining Institute, Plac Gwarków 1, 40-166 Katowice, Poland;

[2] Doctorate Program on Economics and Enterprise, University of Oviedo, Independencia 13, 33004 Oviedo, Spain;

[3] Faculty of Organization and Management, Silesian University of Technology, Roosevelt 26, 41-800 Zabrze, Poland;

[4] School of Mining, Energy and Materials Engineering, University of Oviedo, Independencia 13, 33004 Oviedo, Spain;

关键词: raw material;    price forecasting;    artificial neural network;    predictor variable;    lagged variable size;    rolling window;   

DOI  :  10.3390/en13082017

来源: DOAJ

【 摘 要 】

This paper applies a heuristic approach to optimize the predictor variables in artificial neural networks when forecasting raw material prices for energy production (coking coal, natural gas, crude oil and coal) to achieve a better forecast. Two goals are (1) to determine the optimum number of time-delayed terms or past values forming the lagged variables and (2) to improve the forecast accuracy by adding intrinsic signals to the lagged variables. The conclusions clearly are in opposition to the actual scientific literature: when addressing the lagged variable size, the results do not confirm relationships among their size, representativeness and estimation accuracy. It is also possible to verify an important effect of the results on the lagged variable size. Finally, adding the order in the time series of the lagged variables to form the predictor variables improves the forecast accuracy in most cases.

【 授权许可】

Unknown