Is it possible to forecast behaviour? All you need to know about new AI technology that says yes Is it possible for machines to predict human behaviour? All you need to know about new AI technologies | Photo credit: iStock Images KEY POINTSA recent study reveals that artificial intelligence (AI) can predict human behaviour. Columbia University School of Engineering and Applied Science researchers led the investigation. Thousands of hours of video were processed by the machine for the study.

Humans have a multitude of characteristics that distinguish them from other animals. While science advances and technology are built to capture and adapt human qualities, numerous mysteries of the human brain remain unsolved. Predicting someone's behaviour is a difficult task.

Our algorithm is a step toward machines being able to make better predictions about human behaviour, and thus better coordinate their actions with ours. Our results open a number of possibilities for human-robot collaboration, autonomous vehicles, and assistive technology.

The study facilitates the development of an intuitive sense in machines to enable the prediction of events based on analysis of actions. For the study, the system spent thousands of hours analyzing several videos ranging from sports, movies, and TV shows such as "The Office". Prediction of follow-up behaviour for fist bumps and handshakes was recognized by the system.

In case of uncertainty of future events, humans tend to become cautious. The system was able to acquire the ability to reason about the unpredictability of the future. In geometry, one may not always predict the course of a line such as in that of straight and parallel lines. This concept was used to design the AI model framework. The prediction made can be specific or generic based on the type of data provided for analysis.

Ruoshi Liu, co-lead author of the study said, “Trust comes from the feeling that the robot really understands people. If machines can understand and anticipate our behaviours, computers will be able to seamlessly assist people in daily activity."

This study can certainly pave the way to further developments in the field of Artificial Intelligence (AI) and help bridge the gap between technology and humans.

(This is a slightly modified version of an article originally published in Times Now News. The original article can be found at