Stock market prediction using natural language processing

Abstract

A method of using natural language processing (NLP) techniques to extract information from online news feeds and then using the information so extracted to predict changes in stock prices or volatilities. These predictions can be used to make profitable trading strategies. Company names can be recognized and simple templates describing company actions can be automatically filled using parsing or pattern matching on words in or near the sentence containing the company name. These templates can be clustered into groups which are statistically correlated with changes in the stock prices. The system is composed of two parts: message understanding component that automatically fills in simple templates and a statistical correlation component that tests the correlation of these patterns to increases or decreases in the stock price. The methods can be applied to a broad range of text, including articles in online newspapers such as the Wall Street Journal, financial newsletters, radio &TV transcripts and annual reports. In an enhanced embodiment of the system statistical patterns in Internet usage data and Internet data such as newly released textual information on Web pages are further leveraged.

What is claimed: 
     
         1 . A method of implementing trades based on predicted investment behavior, comprising:
 extracting, using a natural language processing algorithm implemented by at least one processor, information from news media relating to a particular investment by parsing or pattern matching on words in said news media to identify natural language text describing activities or announcements relating to the particular investment that is in or near sentences containing a name of the particular investment and to automatically fill templates with the natural language text extracted by the natural language processing algorithm;   clustering, using a clustering algorithm implemented by the at the least one processor, at least some of the templates into groups that are statistically correlated with changes in investment price or volatility of the particular investment;   determining, using a statistical model implemented by the at least one processor, a statistical correlation of the changes in investment price or volatility of the particular investment within a trading strategy based on historical data in the clustered templates;   predicting, using a metric implemented by the at least one processor, changes in price or volatility of at least the particular investment based on new information about the particular investment and the historical data correlated within the trading strategy where information of the type included in the new information has in the past caused a statistically significant change in the investment price or volatility in the particular investment;   constructing or updating at least one trading rule for the particular investment based on the predicted changes in price or volatility of at least the particular investment; and   automatically executing, using the at least one processor, a trade of the particular investment when the at least one trading rule has been satisfied.   
     
     
         2 . The method of  claim 1 , wherein predicting changes in price or volatility of at least the particular investment based on new information about the particular investment and the historical data correlated within the trading strategy where information of the type included in the new information has in the past caused a statistically significant change in the investment price or volatility in the particular investment comprises notifying and presenting to a human predicted changes in price or volatility of at least the particular investment based on the new information about the particular investment.