Parameter analysis of hybrid intelligent model for the prediction of rare earth stock futures

Because of rare earth futures stock variability and uncertainty of the market, many investors hope to be able to predict the price of rare earth futures on the stock market in the future. The neural network does do better than others in short-term forecasting, and there is no need to establish a complex nonlinear mathematical model and relationship. Based on these advantages, this paper uses the neural network based on genetic algorithm to predict the closing price of rare earth stock by analyzing the historical data of rare earth stock. In the genetic algorithm, the parameters such as crossover rate, mutation rate, iterations and population size are analyzed. Based on the parameter analysis results, a hybrid machine learning model which is suitable for the prediction of rare earth stock is established, which provides a reference for the investors.