Dynamic time warping

The main reason for people investing in the stock market is to make a profit, which requires accurate information about the stock market, price changes and predicting its future trend. Therefore, investors need powerful and reliable tools for forecasting Stock prices in the future. The main purpose of this study is to present a method based on wavelet denoising and dynamic time warping to identify the stock price pattern in the Tehran Stock Exchange. In this regard, first, using the wavelet denoising preprocessing step, noise is removed from the stock price time series, and then the extracted data is used as input to the dynamic time warping prediction model. MATLAB software version 9.11 was used to analyze the research data. The statistical population of the present study includes 3 shares among the shares of steel industry companies of Tehran Stock Exchange. The research was conducted in the period 1395 to 1398. The results show that the predictions obtained from the dynamic time warping method equipped with the wavelet denoising preprocessing step in comparison with the predictions obtained from the dynamic time warping method without the wavelet denoising preprocessing step in all three shares studied, have been associated with much less accuracy and error.