چکیده:
The prediction of future fluctuations in stock index can provide information about the future trend in the capital market. In order to increase the accuracy of the prediction of stock exchange index، this study used a combination of statistical methods and artificial intelligence. In this study، a hybrid stock index prediction model by utilizing principal component analysis (PCA)، support vector regression (SVR) and particle swarm optimization (PSO) is proposed. In the proposed model، first، the PCA is used to deal with the nonlinearity property of the stock index data. The proposed model utilizes PCA to extract features from the observed stock index data. The features which can be used to represent underlying/hidden information of the data are then served as the inputs of SVR to build the stock index prediction model. Finally، PSO is applied to optimize the parameters of the SVR prediction model since the parameters of SVR must be carefully selected in establishing an effective and efficient SVR model. The findings show that preprocessing the data can decrease the prediction error of the model significantly.
خلاصه ماشینی:
Prediction of the Tehran Stock Exchange Index using a combination of Principal Component Analysis, Support Vector Regression, and Particle Swarm Optimization methods 1 4 Reza Raei, 1 Ali Nikahd Ghosraei 3 and Mostafa Habibi Abstract Predicting future fluctuations of the stock index can provide information regarding the future trend of the capital market.
Given the time-consuming nature and low efficiency of manual parameter selection by the user, the Particle Swarm Optimization method, which is a powerful algorithm in the field of optimization, has been used to select the optimal combination of the Support Vector Regression model parameters.
Due to the large volume of input data to the model, to reduce learning time and increase prediction accuracy, preprocessing was performed on the input variables using the Principal Component Analysis method, converting them into principal components.
Keywords: Stock index, Principal Component Analysis, Support Vector Regression, Particle Swarm Optimization, Prediction Article DOI code: 1022051/jfm.
However, since many variables can be identified as having an effect on the stock market index and also because the index time series does not follow a linear pattern, a combination of statistical methods and artificial intelligence has been used in this research to reduce prediction error.
(2013) in an article titled "Index Prediction with a Hybrid Model of Independent Component Analysis and Support Vector Regression with Particle Swarm Optimization" addressed the prediction of stock indices in China, Taiwan, and India.
(
, 
, 
)
