Hybrid Momentum and Markov Switching models for stock price trend prediction

The stock market can be analyzed in two ways, fundamental and technical methods. In this research, the Markov Switching and Randomness models, which are random walk models, are used to predict stock prices. In this research, information from 30 major Tehran Stock Exchanges has been used on a daily basis over the period from 2010 to 2017, with a total of 1562 observations. In this research, we first used the Markov Switching method to predict stock prices. Then, using the Momentum approach and the Randomness method, we created an optimal portfolio of these 30 companies. Based on the results of the 5 companies that had the lowest Randomness, we used stock portfolios. The results of the prediction error in the two models represent the fact that the accuracy of the optimized portfolio has a more accuracy. The result is suggested; according to the efficiency of the momentum method is proportional normally, investors will use the trend of this series to better predict stock returns than normal series.