Designing a combined Markov-Bayesian model in order to predict stock prices in the stock exchange

Investing in shares offered on the stock exchange is one of the most profitable options in the capital market. The stock market has a non-linear and chaotic system that is influenced by political, economic, and psychological conditions. Forecasting time series, such as stock price forecasting, is one of the most important problems in the field of economics and finance because the data is unstable and has many variables that are influenced by many factors. There are many ways to predict stock prices. Non-linear intelligent systems such as artificial neural networks, fuzzy neural networks, and genetic algorithms can be used to predict stock prices. In this research, a hybrid system based on Bayesian networks and the Markov model is proposed to predict the daily trend of the stock market. Bayesian networks are used to specify relationships between variables in forecasting. Finally, the Markov model is used to predict the market trend in the sets extracted from the Bayesian network. The evaluation criteria in the proposed system show the high efficiency of this method.