Combination Forecast of Soybean Futures Data of Dalian Commodity Exchange based on Entropy Weight Method

Abstract

As financial markets continue to develop, the need for accurate predictions in the futures market is growing. This paper takes the soybean futures of Dalian Commodity Exchange (DCE) as the research object, and uses the induced ordered weighted average (IOWA) operator combined with time series analysis and machine learning methods to construct a combined forecast model. First, multiple single prediction models are established through preprocessing and feature extraction of historical data. Secondly, the IOWA operator is used to integrate the results of each single prediction model to optimize the prediction performance. Experimental results show that compared with traditional prediction methods, the combined prediction model proposed in this paper has significant advantages in prediction accuracy and stability. In addition, this model can effectively capture market dynamics and provide investors with more reliable decision-making support. This article not only enriches the theoretical research on futures market forecasting, but also provides new perspectives and tools for practical operations.