فهرست مطالب مهرداد خامی

In this research we propose and implement a fusion model by combining the Hidden Markov Model (HMM), Genetic Algorithms (GA) and Markov chain concept to forecast financial market behavior. The developed tool can be used for in depth analysis of the stock market. We draw on GA to optimize the initial parameters of HMM. The trained HMM is used to identify and locate similar patterns in the historical data. The price differences between the matched days and the respective next day are calculated. Finally, by using Markov chain concept the price differences of similar patterns is obtained to prepare a forecast for the required next day. Forecasts are obtained for a number of shares of Tehran stock exchange and are compared with a conventional forecast method.