Novel information fusion model for simulating the effect of global public events on the Sino-US soybean futures market

Trade frictions and global public health security events have made it more difficult for investors to generate positive returns from the Sino-US soybean futures markets. This paper employed deep learning and mode decomposition to improve market efficiency and reduce investor risk from Sino-US trade frictions and the COVID-19 pandemic using soybean futures data published on the Dalian Commodity Futures Exchange (DCE) and the Chicago Board of Trade (CBOT). The proposed model was found to assist investors to proactively perceive the market risks from disruptive events and make profitable decisions. The results provide practical guidance for the conduct of quantitative trading on the soybean markets between the two countries.