China commodity price index (CCPI) forecasting via the neural network

Forecasting commodity prices is a vital issue to a wide spectrum of market participants and policy makers in various economic sectors. In this work, we investigate the forecast problem by focusing on the China commodity price index (CCPI). We examine the weekly price index series spanning a 15-year period of June 2, 2006–February 26, 2021 through the nonlinear auto-regressive neural network model. We explore forecast performance corresponding to a variety of settings over algorithms for model estimations, numbers of hidden neurons and delays, and ratios for splitting the data. We arrive at a model that is relatively simple and generates forecasts of high accuracy and stabilities. Particularly, we reach relative root mean square errors (RRMSEs) of 1.33%, 1.32%, and 1.32% for model training, validation, and testing, respectively, and an overall RRMSE of 1.33% for the whole sample. Our results could, on the one hand, serve as standalone technical price forecasts. They could, on the other hand, be combined with other (fundamental) forecast results for forming perspectives of price trends and carrying out policy analysis.