Narrow Results

Grain price forecasting is significant for all market participants in managing risks and planning operations. However, precise forecasting of price series is difficult because of the inherent stochastic behavior of grain price. In this paper, a novel hybrid stochastic method for grain price forecasting is introduced. The proposed method combines decomposed stochastic time series processes with artificial neural networks. The initial parameters of the hybrid stochastic model are optimized by a random search using a genetic algorithm. The proposed method is finally validated in China’s national grain market and compared with several recent price forecasting models. Results indicate that the proposed hybrid stochastic method provides a satisfactory forecasting performance in grain price series.

The aim of this paper is to bring out a new perspective for Electricity price forecasting. Numerous studies have focused on forecasting the day-ahead or long-term price forecasting of electricity, rather than examine the relationship between energy commodities, by using various methods. Therefore, this study proposes a model-free approach for electricity price forcasting (EPF). The proposed approach is based on Partial Wavelet Coherency (PWC) and Multiple Wavelet Coherency (MWC) method. These methods are capable of uncovering the coherent time intervals simultaneously for time and frequency domains between the examined time series. VARMA uses the coherent time intervals and outperforms its univariate counterpart (ARMA), both in point and interval forecasting.

Energy index price forecasting has long been a crucial undertaking for investors and regulators. This study examines the daily price predicting problem for the new energy index on the Chinese mainland market from January 4, 2016 to December 31, 2020 as insufficient attention has been paid to price forecasting in the literature for this crucial financial metric. Gaussian process regressions facilitate our analysis, and training procedures of the models make use of cross-validation and Bayesian optimizations. From January 2, 2020 to December 31, 2020, the price was properly projected by the created models, with an out-of-sample relative root mean square error of 1.8837%. The developed models may be utilized in investors’ and policymakers’ policy analysis and decision-making processes. Because the forecasting results provide reference information about price patterns indicated by the models, they may also be useful in building of similar energy indices.