Soybean Futures Price Prediction Based on CNN-LSTM Model of Bayesian Optimization Algorithm

Abstract

In recent years, the complex international environment and economic situation have made soybean futures prices increasingly unstable, which is not conducive to financial stability. Therefore, this paper uses a BO-CNN-LSTM model to accurately predict soybean futures prices and to manage price fluctuations for investors and governments. Firstly, LSTM network is employed to predict soybean futures prices using the local features extracted by CNN network. In addition, CNN-LSTM hyperparameters are optimally solved using Bayesian optimization algorithms. Finally, the constructed model is compared with BP neural network, LSTM model and CNN-LSTM model. This paper selects the basic daily data of the soybean futures contract No.1 of Dalian Commodity Exchange from 2014 to 2021 for research. According to the results, CNN-LSTM models based on Bayesian optimization algorithms perform best. Compared with the basic CNN-LSTM model, MAPE increased by 44.17%, RMSE increased by 24.61%, MAE increased by 41.48%, and R2 increased by 0.06%, which demonstrates Bayesian optimization's superiority.