Provide a model for predicting noisy stock price time series using singular spectrum analysis, support vector regression with particle swarm optimization and compare it with the performance of wavelet transform, neural network, moving average self-regression process and polynomial regression

In this research, a model for analyzing and predicting the noisy financial time series of stock prices using singular spectrum analysis and support vector regression along with particle swarm optimization is presented. Thus, the time series of closed prices of 140 shares of companies in different industries per minute per day for the period from 28 May to 11 June for the years 1392 to 1398 was examined separately from the Tehran Stock Exchange. Also, the performance of the proposed model was compared with the performance of four wavelet transform models with neural network, moving average regression process, polynomial regression and naïve model. Mean absolute error, mean absolute error percentage, and mean square root of error were used as the main performance criteria. The results show that the performance of the proposed model for analyzing and predicting noisy financial time series based on mean absolute error, mean absolute error percentage and mean square root of error is better than other models (including: wavelet transform, moving average self-regression, regression Polynomial is the naïve model).