Traders cannot predict the market, but perhaps their faces can

“Everyone on the street is talking,” says a trader in London (not part of the study), who said he would find such warnings about the mood of his colleagues useful. “All part of our job is discussing ideas and exchanging information… The non-verbal communication is tremendous.” Years ago, trading floors were noisy places, with people often talking on three or four phone lines at once; Now many communicate through chat rooms and talking is minimal.

But the study also points to another troubling phenomenon: facial recognition is here to stay, and so may its more controversial cousin, facial analysis. For all our concerns about facial recognition, including the mistakes it can make as a surveillance tool, tens of millions of us still use it to unlock our phones without hesitation.

“We have a whole toolbox of search algorithms that we will test to see if they correlate with a market signal.”

Mario Savvides, lead scientist of the project

A facial analysis, such as that used by Carnegie Mellon, opens a larger worm box. Last summer, Microsoft promised to eliminate its facial analysis tools, which estimate a person’s gender, age and emotional state, admitting that the system could be unreliable and invasive. That may not matter all that much to traders looking to collect all the data they can use to an advantage. But this study, if successful, could encourage researchers to analyze faces for other purposes, such as assessing one’s emotional state during a work meeting.

“When you close a deal on Zoom, can you have an AI read your face to see if someone is bluffing you or being a tough negotiator?” asks Savvides. “It’s possible. Why not?”

Zoom Video Communications introduced a feature last year that tracks sentiment in a recorded work meeting. Called Zoom IQ, the software, aimed at sales professionals, gives meeting attendees a score between 0 and 100, with anything over 50 indicating greater engagement in the conversation. The system doesn’t use facial analysis, but instead tracks speaker engagement or how long to wait for a response, and offers their score at the end of the meeting.

More than two dozen rights groups have urged Zoom to halt work on the feature, arguing that the sentiment analysis is pseudoscientific and “inherently biased.” A spokesperson for Zoom said the company is still selling the software and turning “customer interactions into meaningful insights.”

You can argue that Carnegie researchers shouldn’t care what their facial analysis tool tells them about traders’ emotions; All you have to do is spot the patterns that indicate correlations and feed those numbers into a search algorithm. But the downside of turning emotions into a number is just that: it risks devaluing one of the most fundamental traits of being human. It might be better if it doesn’t catch on.


The Business Briefing newsletter delivers important stories, exclusive coverage and expert opinions. Sign up to receive it every weekday morning. Traders cannot predict the market, but perhaps their faces can

Brian Lowry

InternetCloning is an automatic aggregator of the all world’s media. In each content, the hyperlink to the primary source is specified. All trademarks belong to their rightful owners, all materials to their authors. If you are the owner of the content and do not want us to publish your materials, please contact us by email – The content will be deleted within 24 hours.

Related Articles

Back to top button