providing a hybrid strategy based on the theory of turbulence and price acceleration in the iranian stock market

Stock prices are influenced by economic, technological, psychological, and geopolitical factors. a literature review in this field reveals that stochastic approaches, trend analysis, and econometrics have been employed to examine stock market dynamics and forecast prices. however, these techniques fail to provide a comprehensive understanding of market dynamics. they disregard the temporal relationship between these factors and are unable to capture their cumulative effects on prices. in order to bridge these gaps, this study integrates chaos theory and continuous data mining based on price acceleration, resulting in the development of a new price forecasting method called the dynamic stock market recognition simulator. this method combines two approaches: one involves incorporating delay structures or time intervals into the dataset, while the other entails selecting new variables to account for the market environment. the results demonstrate that the proposed method can effectively forecast long-term stock prices using a small dataset with limited dimensions.