Recorded Future News Analytics Research Discussed at FT Alphaville | Recorded Future
Predict 21: The Intelligence Summit Register Today

Recorded Future News Analytics Research Discussed at FT Alphaville

July 22, 2010 • Chris

Yesterday, we posted new research derived from our news analytics API finding “FT Alphaville Disproportionally Interesting Compared to General News in Predicting Stock Returns.”

This morning, FT Alphaville correspondents discussed some of the findings during the site’s Market Live chat. Below you can read the conversation between correspondents Neil Hume (NH) and Bryce Elder (BE) related to Recorded Future’s findings:

NH So

NH we are always accused of being bearish, right?

BE We are.

BE what was it that PR guy accused you of yesterday?

BE “running a negative tip sheet”

NH oh yes, so he did

NH well, all that criticism is just plain wrong

NH because the stats say so

BE Stats? What stats?

BE I didn’t think you could operate a spreadsheet.

NH very funny

NH We have some data from an independent source

BE Go on. This sounds interesting.

NH well

NH a company called Recorded Future got in touch a couple of days ago

BE Okay.

NH basically they scan thousands of blogs, news publications, trade rags, financial databases etc

NH then they extract info from the text and see how often things written about occur

BE And?

NH well

NH the results speak for themselves

NH FT Alphaville Disproportionally Interesting Compared to General News in Predicting Stock Returns

NH got that

NH I’ll repeat it

NH FT Alphaville Disproportionally Interesting Compared to General News in Predicting Stock Returns

BE My word. That’s a nice strapline for the adverts.

BE If we had any adverts.

NH well quite

NH might look good in the 6am Cut

NH here are the findings

NH At Recorded Future, we’re using the Web to find new and interesting predictive signals. Central to our research is the concept of a Temporal Analytics Engine – effectively a massive database of structured news data. We’ve harvested articles from the thousands of blogs and news sources for the last several years, done some detailed processing of this data, and put it into our database, ready for further analysis..

NH Let’s look at an example: sparing some of the technical details, it’s pretty easy to ask our API to “Give me all the news, along with sentiment information, related to Goldman Sachs, Amazon.com, Exxon, or Microsoft, published on FT Alphaville, for the month of May 2010.” What you’ll get back is a highly structured data set containing fragments of article text, publish dates, sentiment data (good news or bad news?), a measure of news importance, and lists of other entities involved in each particular document. This data set is machine-readable, and without too much work should be ready to load into your favorite analytics software.

NH The results of my experiments prove fairly interesting. In particular, our “big news” signal is statistically significant at the 0.001 level. This indicates that on average, good news on FT Alphaville is associated with 1-week ahead outperformance. Conversely, on average, bad news for a company on FT Alphaville is associated with 1-week ahead under-performance. The same effect is not evident in our database as a whole, indicating that there is something “special” about the news that comes from FT Alphaville.

NH and here’s the conclusion

NH which I will repeat

NH This research, however preliminary, indicates that there may be a relationship between occurrence of significant news in FT Alphaville and excess stock returns. While this may not be surprising to readers, the real value added here is the ability to quantify the news and analyze it in a statistical fashion.

NH and again

NH This research, however preliminary, indicates that there may be a relationship between occurrence of significant news in FT Alphaville and excess stock returns. While this may not be surprising to readers, the real value added here is the ability to quantify the news and analyze it in a statistical fashion.

BE Blimey.

BE and he’s not even looked at Muppet Alpha yet

NH I know

NH if you want to read the full article go here

NH So never again

NH can people call us negative

NH of course

NH I have no idea how it works

NH but it looks complex

NH so it must work

If you’re interested in Recorded Future’s statistical applications, predictive analysis and trading signals, visit our Predictive Signals quant blog. Or visit our site to learn more about Recorded Future’s news and media analytics capabilities.

New call-to-action

Related Posts

How The Stadtwerke Klagenfurt Group Reduces Risk to Critical Infrastructure

How The Stadtwerke Klagenfurt Group Reduces Risk to Critical Infrastructure

November 17, 2020 • The Recorded Future Team

Key Takeaways The Stadtwerke Klagenfurt Group delivers essential municipal services,...

Security Intelligence Handbook Chapter 2: Examining Operational and Strategic Security Intelligence

Security Intelligence Handbook Chapter 2: Examining Operational and Strategic Security Intelligence

November 12, 2020 • The Recorded Future Team

Editor’s Note: Over the next several weeks, we’re sharing excerpts from the third edition of...

How Predict 2020 Disrupted the Status Quo

How Predict 2020 Disrupted the Status Quo

October 9, 2020 • The Recorded Future Team

While Predict 2020 looked a bit different this year, the world’s largest security intelligence...