Stock price prediction method based on genetic algorithm and long-short-term neural network

Abstract

According to the method, feature selection is carried out on massive stock factors based on a genetic algorithm (GA), an optimal factor combination suitable for a current scene is selected, and deep learning is carried out by adopting a long-short-term neural network model (LSTM), so that high-precision prediction of the stock price is achieved. According to the genetic algorithm, an adaptive heuristic search mechanism is introduced based on natural selection and genetic evolution thought, and an approximately optimal solution of an optimization problem with a large search space is searched. In the population propagation process, combination crossover and variation are carried out by means of a genetic operator of natural genetics, and according to the principle of survival of fittest andelimination of advantages and disadvantages, an increasingly good approximate solution is generated through generation-by-generation evolution. The long-term and short-term neural network model is widely applied to a time sequence prediction model due to long-term memorability, and the prediction precision can be effectively improved by searching for the complex nonlinear relationship between thestock factor and the stock price through deep learning.

Description

technical field [0001] The invention relates to the field of deep learning, constructs a stock price prediction method based on a genetic algorithm and a long-short-time neural network, and can effectively improve stock prediction accuracy. Background technique [0002] With the rapid development of social economy, the number of listed companies is increasing, and stocks have become one of the hot topics in the financial field. The changing trend of stocks often affects the direction of many economic behaviors to a certain extent. Therefore, the stock price forecast It has also attracted the attention of more and more scholars. There are many factors that affect stock prices. With the maturity of statistical techniques in the financial field, financial scholars have excavated a large number of stock market impact factors and quantified them into specific data for research on stock trends. [0003] With the support of massive financial data, it is possible for the realizatio...

AI Technical Summary

Problems solved by technology

Second, difference

Random forest and support vector machine algorithms cannot solve the timeliness and variance of financial data

Images