Journal
RESOURCES POLICY
Volume 73, Issue -, Pages -Publisher
ELSEVIER SCI LTD
DOI: 10.1016/j.resourpol.2021.102222
Keywords
Non-ferrous metals; Interval prediction; Artificial intelligence; Multi-objective optimization algorithm; Distribution function
Categories
Funding
- Major Program of National Social Science Foundation of China [17ZDA093]
Ask authors/readers for more resources
This paper investigates the price fluctuations and prediction methods of non-ferrous metals, proposes a hybrid point prediction system, and establishes an uncertainty prediction framework. Empirical results show that the framework has better predictive power for non-ferrous metals price prediction.
As a bulk product with huge international circulation, non-ferrous metals have frequent and severe price fluctuations, which have attracted great attention from academia and industry. However, the non-ferrous metal price series has strong volatility and nonlinear characteristics, which makes the realization of high-precision forecasts still a difficult and challenging problem. In this paper, a hybrid point prediction system is constructed to achieve high precision point prediction results. Moreover, uncertain forecasts contain more information and can provide market participants with more detailed guidance, but uncertainty forecasting is often ignored in practice. Based on the high precision point prediction system, the uncertainty prediction framework is proposed in this paper. Different distribution functions were used to analyze the distribution characteristics of the data, and the uncertainty prediction at different levels was successfully realized according to point prediction results. To verify prediction performance of the proposed prediction framework, multiple contrast experiments have been carried out using the London Metal Exchange daily future prices of Zinc, Copper and Lead. The empirical results show that the developed prediction framework has better predictive power for non-ferrous metals price prediction.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available