There’s a new algorithm that will alert Wall Streeters when they start freaking out. (2016)

“…traders who expressed too little or too much emotion made relatively poor trades.

Rachel Butt (reporting the work of professor Brian Uzzi, Kellogg School of Management and colleagues Bin Liu of Google, and Ramesh Govindan, Northwestern University, Illinois.)
Business Insider UK, 22 September 2016

This article relates to items we’ve uploaded (notably by Dr John Coates) on the way hormones affect traders’ behaviour. It also relates to items on linguistic biomarkers as a tool for identifying potential hubris in leaders.

“Emotions color the way we view and interpret fact. They also impact our ability to take risks once we make a decision on a rational ground.

“Uzzi and his team sifted through 1.2 million instant messages among day traders over a two-year period… traders who expressed too little or too much emotion made relatively poor trades….

“Using a dictionary to assess the level of emotional activation in the day traders’ messages, (the researchers) concluded that the best trades came when people hit the medium level of emotional activation – traders expressing neither very little emotion, nor an overly large amount of feelings.

“That kept them clear-headed enough but at the same time allowed them to react appropriately to risks,” Uzzi said.

“(Building on this research) Uzzi has developed a system that could alert traders or their respective companies of their emotional states – through analyzing their emails and instant messages in real time.

“… Those real-time analytics can then sent directly to the traders or head office of a trading floor, allowing the higher-ups to assess if they should intervene in the market or not.

“There’s a whole body of work in psychology that says based on the language that we use to describe our situation, we’re revealing our underlying emotional state,”

“What our system does it to take unstructured text data that’s coming from human communication (and create) new quant data that you didn’t have before.”

Access the full article here: There’s a new algorithm that will alert Wall Streeters

Access the original research article here: Do emotions expressed online correlate with actual changes in decision-making?