Influence of different factors on prices of upstream, middle and downstream products in China's whole steel industry chain: Based on Adaptive Neural Fuzzy Inference System

Abstract

The steel industry in China has been developing slowly, and the prices of this industry’s products have recently fluctuated. To predict the trends of price changes in the future, we must discover the factors that play leading roles in determining prices. In this paper, an adaptive neuro fuzzy inference system (ANFIS) is used to measure the factors influencing the prices of steel products in China's upper, middle and lower reaches from the perspective of the whole industry chain and to identify the most influential variables. The analysis uses daily data pertaining to relevant variables from December 2013 to October 2017 and selects the upper, middle and lower reaches of iron ore, ferrosilicon and rebar as the research objects. The results show that the main factors affecting steel products at different stages are varied. The most significant factors affecting the prices of upstream products, midstream products and downstream products are midstream product prices, market supply and demand, and inventory, respectively. Therefore, from the perspective of the whole industry chain, when the prices of upstream products are high, China should regulate the prices of midstream products. For midstream products, China can consider improving the market structure to improve supply and demand. In response to rising prices of downstream products, China should optimize its inventory structure. This paper provides policy suggestions for the regulation and control of the development of the steel industry.