Method of predicting a composite stockrelated price index through an analysis of a social data and system applying the same

摘要

The present invention relates a method and a system for predicting a composite stock price related index whereby prediction results with adaptability and reliability can be obtained even when huge market fluctuation occurs by favorable or unfavorable issues on stock types which were not reflected to prediction of the composite stock price related index. According to an embodiment of the present invention. The method includes the steps of: (a) appointing at least one stock type for prediction of the composite stock price related index; (b) predicting the stock price indexes with respect to each stock type using big data consisting of structured data, including economy statistical data, and unstructured data, including social media data (SMD); (c) predicting the composite stock price related index based on the predicted stock price indexes for each stock type; (d) calculating difference between the composite stock price related index, predicted in step (c), and an actual composite stock price related index; (e) determining whether the difference is over a predetermined threshold value; and (f) replacing a portion or the whole of the stock types with other stock types when the difference is over the predetermined threshold value. The composite stock price related index is predicted by analyzing social data.