Patent attributes
Provided are a method and a system for predicting stock fluctuation prediction. A system for predicting stock fluctuation according to an embodiment of the present invention includes: a data collector and a preprocessor collecting news and KOSPI data and extracting words from the collected news through stopword removal and morphologic analysis, a sentiment dictionary constructor selecting sentiment words and calculating sentiment values of the sentiment words to construct a sentiment dictionary of a stock domain required for stock prediction, and a stock fluctuation prediction model constructor predicting fluctuation of a closing price of a next day to a closing price of a current day by combining a prediction model using the constructed sentiment dictionary and an ARIMA prediction model using the KOSPI data.
