Monday, January 12, 2015

Robot Writing Moves from Journalism to Wall Street

From MIT's Technology Review:

Software that turns data into written text could help us make sense of a coming tsunami of data. 
Software that was first put to work writing news reports has now found another career option: drafting reports for financial giants and U.S. intelligence agencies.

The writing software, called Quill, was developed by Narrative Science, a Chicago company set up in 2010 to commercialize technology developed at Northwestern University that turns numerical data into a written story. It wasn’t long before Quill was being used to report on baseball games for TV and online sports outlets, and company earnings statements for clients such as Forbes.

Quill’s early career success generated headlines of its own, and the software was seen by some as evidence that intelligent software might displace human workers. Narrative Science CEO Stuart Frankel says that the publicity, even if some of it was negative, was a blessing. “A lot of people felt threatened by what we were doing, and we got a lot of coverage,” he says. “It led to a lot of inquiries from all different industries and to the evolution to a different business.”

Narrative Science is now renting out Quill’s writing skills to financial customers such as T. Rowe Price, Credit Suisse, and USAA to write up more in-depth, lengthy reports on the performance of mutual funds that are then distributed to investors or regulators.

“It goes from the job of a small army of people over weeks to just a few seconds,” says Frankel. “We do 10- to 15-page documents for some financial clients.”

An investment from In-Q-Tel, the CIA’s investment division, led the company to work from multiple U.S. intelligence agencies. Asked about that work, Frankel says only that “The communication challenges of the U.S. intelligence community are very similar to those of our other customers.” Altogether, Quill now churns out millions of words per day.

The software’s output can be impressive for software, but it can’t write without some numerical data for inspiration. It performs statistical analysis on that data, looking for significant events or trends, and it draws on knowledge about key concepts such as bankruptcy, profit, and revenue, and how such concepts are related.

The following paragraph, from an investment report, shows that Quill can write passable text for such a document, but it can still feel as if it were written by a computer.
“The energy sector was the main contributor to relative performance, led by stock selection in energy equipment and services companies. In terms of individual contributors, a position in energy equipment and services company Oceaneering International was the largest contributor to returns. Stock selection also contributed to relative results in the health care sector. Positioning in health care equipment and supplies industry helped most.”
Quill is programmed with rules of writing that it uses to structure sentences, paragraphs, and pages, says Kristian Hammond, a computer science professor at Northwestern University and chief scientist at Narrative Science. “We know how to introduce an idea, how not to repeat ourselves, how to get shorter,” he says....MORE

Related:
And Here Come the Robo-journalists "The CIA Invests in Narrative Science and Its Automated Writers"
...If you’d like to see an example of their stuff, you can head to Forbes, which is using Narrative Science to create automated earnings reports and previews, like this look-ahead at Smucker’s prospects for tomorrow....MORE 

Now we just run that product through the low latency Thompson Reuters machine readable newsfeed, deliver to the SEMLAB algos, apply some news analytics and... hey wait! Somebody could lose their job! 
Sure, MoneyBeat Says Their Posts Are Not Written by Robots But How Can We Know?
"Reuters gutting web infrastructure for 'Reuters Next,' its big online retooling"
How can I ever trust an ultra-low latency direct feed of machine readable news designed solely for application consumption again? 
Robo-journalists: Beyond the Quakebot
Automating the Newsroom: The AP's Robot Copy Editor
Washington Post considered using robot sportswriters
New York Fed: The Relationship Between News and Asset Prices Has Been Changing Over Time
Nanoseconds for All? UBS BizDev Says HFT Will Diffuse to Asset Managers (when do mom and pop go low latency?)
Anomaly: Newspaper Content Can Predict Stock Market Returns
McKinsey: Monetizing Freely Available Data (worth $3.2-$5.4Trillion per year)
A Deep Dive Into the Future of RoboAnalysts (will entry level hedgies still command $353K to start?)