Energy market prediction with novel long short-term memory network: Case study of energy futures index volatility

Lihong Zhang, Jun Wang and Bin Wang

Energy, 2020, vol. 211, issue C

Abstract: Energy futures that is no less influential than the spot market is an important part of commodity futures. A novel ST-LSTM model based on long short-term memory network (LSTM) model is proposed to improve the prediction accuracy of energy futures index. In the process of establishing this model, stochastic time strength function that represents different effects on current and future information at various times is introduced into weights and errors of LSTM model, which makes the model more consistent with the randomness and volatility of futures markets. The empirical research, including six evaluation prediction criteria and fitting curve methods, verifies that the prediction accuracy is improved by ST-LSTM model. Furthermore, a new multi-scale complex synchronization method q-MCCS is proposed to evaluate the models. The ST-LSTM model is also utilized to predict the energy futures price of different time interval lengths, such as one month, three months, six months and one year, which demonstrates that the longer the time interval length is and the less volatile the energy futures price is, the superior the forecast effect is.

Keywords: Energy market prediction; Commodity energy futures; Stochastic time strength; Deep learning prediction; Long and short-term memory; Multi-scale complex synchronization (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (6)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544220317424
Full text for ScienceDirect subscribers only

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:eee:energy:v:211:y:2020:i:c:s0360544220317424

DOI: 10.1016/j.energy.2020.118634

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().