fbpx

Trading On News Sentiment Analysis in High Frequency Trading HFT

(Last Updated On: May 3, 2012)

Trading On News Sentiment Analysis in High Frequency Trading HFT

Thomson Reuters doesn’t just publish news — it now reads the news as well, measures sentiment with sophisticated linguistic analytics and distributes the results to both algorithmic trading engines and real live human traders. This is a big step beyond news services which distribute simple news elements such as corporate earnings or unemployment figures that can be read by trading systems.

High frequency trading (HFT) engines can take sentiment data feeds based on automated analysis of news and electronic media along with market data and news from Thomson Reuters.

Called Thomson Reuters News Analytics , the sentiment analysis places it in a different world from elementized news feeds which works with more structured types of text such as earnings, employment figures or events that can be tagged for consumption by trading engines. Thomson Reuters has long offered a company events feed. Its sentiment analysis is used by scores of clients, about 75 percent of them running quant strategies and most of those in the HFT world. Rest of the clients uses it in their trading desk to quickly react to the news sentiments.

Behind the sentiment is a lot of powerful processing and recently developed skills in reading news by computer and understanding it. The feed is even able to understand sarcasm, placing it ahead of a lot of people.

The trading signals from analyzing this data are incremental to other factors already incorporated into their investment and trading models such as price, momentum, trading volume, and analysts’ revisions. Traders can plug the data directly into their algo engines or use it to analyze a situation and make their own [human] decisions.

Thomson Reuters started looking at how to incorporate sentiment into a data feed in 2006. It began working with Lexalytics, which had spent several years developing software to read and understand unstructured text. While people can rate 6 to 10 articles per hour, Thomson Reuters and Lexalytics developed a way to automate the process and analyze 6 to 10 articles per second, making the activity much more useful for financial services.

Thomson Reuters gave sample data from Lexalytics to several clients to see if the results were useful was interesting. The users reported that it created an alpha-generating signal, so Thomson Reuters brought the product to market as a white-labeled solution and worked with Lexalytics to train the system for financial services language.

Most of Thomson Reuters users are in high frequency trading, but we have also seen a number which use the sentiment to help human analysts and traders evaluate the data, often through compelling visualizations, like those offered from Panopticon.

Even in a highly demanding, data intensive world, sentiment can add significant value.

Thomson Reuters News Analytics Advantage:
Uniquely powerful technology – Powered by an unparalleled natural language processing system from linguistics technology innovator Lexalytics, Thomson Reuters News Analytics scores text across the following primary dimensions:
• Author sentiment – metrics for how positive, negative or neutral the tone of the item is, specific to each company in the article
• Relevance – how relevant or substantive the story is for a particular item
• Volume analysis – how much news is happening on a particular company
• Uniqueness – how new or repetitive the item is over various time periods
• Headline analysis – denotes special features such as broker actions, pricing commentary, interviews, exclusives, and wrap-ups, among many others

http://thomsonreuters.com/content/financial/pdf/enterprise/News_Analytics.pdf

 

==

Top Most Product avilable in this class is — Alpha Flash
http://www.alphaflash.com/http://www.alphaflash.com/product-info

 

=

The key differentiating factor for Thomson Reuters is the level of cross-asset and geographies coverage . Also, TR has great coverage for Rapidly Developing Economies such as India, China, Brazil, etc. Of a notable mention, Thomson Reuters breaks the story first than the competition across the globe. The same can be found in the following link http://www.reutersfirsts.com.

 

==

Does the algo also look at non-traditional news sources like social media or only looks at Thomson Reuters prop. news sources ?

==

Just yesterday only I came across this product …..www.modulusfe.com/wallstreetbirds/ is a real-time Social Media Trading Software..

 

NOTE I now post my TRADING ALERTS into my personal FACEBOOK ACCOUNT and TWITTER. Don't worry as I don't post stupid cat videos or what I eat!

Subscribe For Latest Updates

Sign up to best of business news, informed analysis and opinions on what matters to you.
Invalid email address
We promise not to spam you. You can unsubscribe at any time.

NOTE!

Check NEW site on stock forex and ETF analysis and automation

Scroll to Top