CFO’s Tech Companies to Watch 2018: Prattle

Prattle's natural language processing analyzes earnings calls to help predict their effect on market movements.
David McCannMay 2, 2018
CFO’s Tech Companies to Watch 2018: Prattle

We combed through websites, interviewed tech experts, and researched a host of product categories to assemble, once again, the roster of 20 companies that make up our annual “Tech Companies to Watch.” We uncovered a wide range of technologies and products that would be valuable to finance chiefs, and we also discovered a wealth of innovation going on in “traditional” finance-related tech categories.

The entirety of the list appears in the April/May 2018 edition of CFO magazine. We are revealing the first 10 companies on, one per day. Our first company to watch was Pymetrics. Today, we cover Prattle, a linguistic tool that performs sentiment analyses. Other companies on the list appear at the end of the story.

Drive Business Strategy and Growth

Drive Business Strategy and Growth

Learn how NetSuite Financial Management allows you to quickly and easily model what-if scenarios and generate reports.



What corporate executives say during earnings calls matters, obviously. That’s why sentiment analyses exist: investors want to gauge whether the language CEOs and CFOs use on a call is positive, negative, or neutral. But Prattle, a small company that’s starting to make a big splash in the investment research arena, is providing what could be characterized as “sentiment analyses on steroids.”

In late 2016, Prattle launched its first product: an advanced analysis of speeches and other communications by the U.S. Federal Reserve and 19 other central banks. Its clients — asset managers, hedge funds, investment banks — use the data to guide their investment decisions.

Prattle’s algorithms calculate positive or negative scores in terms of their predicted impact on subsequent short-term market movements of various asset classes. The analysis looks at words, sentences, phrases, and the relationships between them to generate a score indicating the speech’s relative dovish or hawkish quality.

That’s not all. Using machine learning and natural language processing, Prattle analyzes how the language patterns in a speech differ from those the speaker used in previous addresses.

The analysis tracks how markets moved after the earlier speeches and, if language patterns are different in the new speech, adjusts the expected market movements accordingly. With each new speech the algorithms are designed to grow more accurate, says Brian Peterson, Prattle’s chief operating officer and de facto finance chief.

An example of a language subtlety that Prattle takes into account involves usage of the words “moderate” and “modest.” How people use those words makes a huge difference in financial markets, according to Peterson. “In a straight-up sentiment analysis, they could both be positive and they’d have the same weighting,” he says. “But in financial market settings, they can have significantly different meanings.”

Prattle upped its game considerably in September 2017 when it began selling access to analyses of the earnings calls of 3,000 U.S. companies that had been publicly held for at least four years. The data has revealed some interesting trends. For one, when a company’s CFO speaks for a larger percentage of the call, compared with the CEO, there is less short-term volatility in the company’s share price. The trend holds true for both positive and negative volatility.

Prattle’s methodology seems to be on the money. A third-party research firm, Lucena Quantitative Analytics, performed portfolio backtests using Prattle data to guide trading strategies. The backtests, which factored in realistic trading conditions such as transaction costs, involved “buying” stocks of companies that Prattle scored as positive and holding them for one month before “selling.”

Applying that strategy to stocks included in the Dow Jones Industrial Average from the beginning of 2013 through mid-September 2017 resulted in a 112% return premium over the Dow’s actual performance.

The same strategy, applied to Russell 1000 stocks from the beginning of 2012 through mid-September 2017, scored a 44% return premium. The Sharpe ratios for the two portfolios, representing risk-adjusted return, were 1.33 and 1.46 — “huge returns over the benchmarks,” says Peterson.

“At its core, the typical sentiment analysis takes all the positive and negative words in a communication, and the net difference is the score,” Peterson says. “Our version is much more mature.”

Prattle may not need many clients to profit from its groundbreaking products. The company’s main assets are the algorithms, and they are developed and refined by a small number of people.

Startup funds were negligible, although last year the company landed $3.3 million in seed funding for its expansion into equities. Now the company is working toward expanding its analyses to company press releases and stocks listed internationally.

Other 2018 Tech Companies to Watch





Adaptive Insights

Duo Security