Natural Gas Price Forecasting using Kriging Interpolation Technique and Neldar-Mead Optimization Algorithm

The prediction of economic series with high volatility and high uncertainty - such as natural gas prices - is always a challenge in econometric models, because the use of traditional linear modeling models does not allow us to predict complex and nonlinear time series. Regarding the prediction of natural gas prices,  findings point to superiority of the neural network compared to regression models. Nevertheless, the main challenge of this method - the possibility of overlapping and noise of data from the system - has kept the choice for an optimal method open. In this study we use the Kriging interpolation  to predict the price of natural gas. For this purpose, after identifying the effective parameters, sampling and normalizing them, we created a Kriging predicting functions  and improved it with the Nelder-Mead optimization technique. ​The results of the study show that the Kriging metamodel provides a more accurate prediction than the artificial neural network prediction model.  Our research findings also suggest that the Neldar-Mead optimization algorithm has somewhat improved the predicted results. However, theextent of this improvement is not remarkable.