Carnegie Mellon researchers in Qatar and Pittsburgh have joined forces to explore the behavior of successful negotiators.
The study uses the Robotics Institute's Panoptic Studio, a two-story geodesic dome that is fitted with 480 synchronized video cameras to capture fine details in human interaction.
John O’Brien, associate dean and associate professor of accounting at CMU-Q, said, “The idea came to us last March when we took a group of students to the Pittsburgh campus. These students were familiar with using technology to solve business problems; they won the Algorithmic Trading Hackathon, a competition where students from different disciplines created algorithms for equity markets. They were already thinking about using technology for problems in business, and the dome seemed like an excellent tool.”
O’Brien turned to Fuad Farooqi, assistant professor of finance, with the idea. O’Brien and Farooqi have collaborated on interdisciplinary projects before: They are the team behind Q-SmartLab, a platform for students of all disciplines to process, interpret and reshape real-time information from the global markets.
Together, they approached Yaser Sheikh, associate professor of robotics, who specializes in dynamic motion reconstruction and human behavior analysis and Hanbyul Joo and Tomas Simon, two Ph.D. students in robotics.
The team designed an experiment where 10 CMU-Q students, in Pittsburgh as part of campus exchange, engaged in a mock trading exercise. Split into buyers and sellers, each participant was aiming for the highest profit at the end of the session.
“This was an opportunity to study negotiations at a higher level,” said Farooqi. The cameras captured the negotiators’ eye contact, movement around the dome, and body language like head and hand gestures.
“We were concerned that the dome would not be able to handle 10 negotiators, but it handled it just fine,” said O’Brien.
The dome generates a half terabyte of data every minute from the cameras and audio feeds. O’Brien and Farooqi’s team are analyzing the visuals first, and they will feed the information back to Sheikh in Pittsburgh so he can use it for machine learning purposes.
In the meantime, the behavior of successful negotiators will be analyzed by the Qatar team.
“If we can understand what behaviors lead to success, we can train business students to be better negotiators,” said O’Brien. “Down the road, these insights could lead to augmented reality applications.”
The team will conduct a second set of trials later this spring.