Stock Price Prediction And Selection Based On Hidden Markov Model

In this paper,we mainly use the hidden Markov model to study the stock price prediction and stock selection in China's stock market from two aspects of technical analysis and basic analysis.In technical analysis,the closing price,opening price,highest price and lowest price of market index or individual stock are selected as the observation sequence of the hidden Markov model.The model is trained with historical data to obtain the optimal number of hidden states and relevant parameters of the model.A hidden Markov model for predicting stock price is established by rolling window.Then,the model of test set is tested,and the results show that the model has good prediction ability.In addition,according to the prediction model,an investment strategy is established and simulated,and good economic benefits are obtained.In basic analysis,we select earnings per share,return on net assets,operating profit rate and net sales interest rate as the observation sequence,and use the financial data to establish a hidden Markov model to predict the financial situation of the company,and test the validity of the model.Then,The investment strategy under the financial situation of company is constructed and simulated.The investment results show that the model and the investment strategy have good profitability.