Investors Employing AI to Analyze Executives’ Speech for Making Market Predictions

By Prakash Gogoi | October 27, 2021
Die-hard anime fan, would watch movies all day long if possible, any genre. The most prized investment ever made in the house is the theater room. If Prakash is not writing, he'll be in there.
50 0
Fund managers are testing out AI-powered software that analyzes body language and speech patterns of company executives to potentially discern true market conditions.
Fund managers are testing out AI-powered software that analyzes body language and speech patterns of company executives to potentially discern true market conditions. (Image: sergeitokmakov via Pixabay)

Investors are reportedly using technology that scrutinizes human behavior in order to make informed decisions about their investments. Technological advances being made in fields like AI and natural language processing (NLP) are making this more possible.

The AI processing capabilities are being used to analyze audible tones, cadence, and how spoken words are emphasized alongside phraseology. Some are specifically designed to analyze interview and speech transcripts through increasingly sophisticated programming.

Near the end of 2020, Evan Schnidman, a language pattern software specialist, used his software to analyze the speech patterns of some IT industry executives. They were making claims that ongoing supply-chain disruptions would not affect the availability of semiconductor chips that are crucial for a number of industries, such as the automobile sector.

“We found that IT sector executives’ tone was inconsistent with the positive textual sentiment of their remarks,” Schnidman told Reuters.

A few months after the executives made their comments, automobile majors, such as Ford and Volkswagen, began sending out warning signals regarding a severe shortage of chips. Consequently, the share prices of most major companies in the industrial and automobile sector took a dive.

NLP is now being used as part of investment decisions. Eleven fund managers interviewed by the Reuters attested that they were either using or at least testing such systems. Many are also making use of algorithmic textual analysis and CIA lie detection techniques to gain an advantage while making stock calls, the trending sentiment in a specific sector, or to gauge the overall market direction.

A company called Business Intelligence Advisors (BIA) has been using a CIA lie detection process for its clients for over a decade now. Founded by former CIA officers, the company continues to recruit staff members from the agency. 

The BIA does analysis on 200 conference calls per quarter for 40 clients. In total, the system has analyzed more than 11,000 conference calls.  

“There is this huge body of content out there produced every quarter and it gets harder and harder to get an edge and investors are looking for every opportunity… We think of it in terms of how much risk is in the communication. Is it reliable and complete, and if less than reliable and complete, we look for patterns in language and behavior and extrapolate about what is driving that risk, which leads to investable decisions,” CEO Cheryl Cook told CNBC.

Slavi Marinov is the head of machine learning at Man AHL, a division of the investment management firm Man Group. Marinov said that NLP is definitely one of the core areas of research that they are currently focusing on. 

“These models transform something that is very messy to something that is easily understandable by a quant,” Marinov said. He believes that over time, executives will be no match for machines that are learning at a higher speed.

Supporters of NLP state that it can unlock valuable insights pulled from the realm of “unstructured data,” including media interviews, analyst calls, and unscripted Q&A sessions. But the technology is still in its infancy. Moreover, not everyone is in a position to adopt the tech right now since these AI systems can require millions of dollars in investment.