Spotting expertise in the eyes: billiards knowledge revealed by gaze shifts and detected through machine learning

In sports, as in other activities and knowledge domains, expertise is highly valuable.We assessed whether expertise in billiards could be deduced from the pattern of eye movementswhen experts, compared to novices, are simply observing a filmed billiard match with no specifictask, and ad-hoc occluded billiard shots with a trajectory prediction task.Experts performed better than novices, both in terms of accuracy and response time. In additionexperts did not need to mentally extrapolate the hidden part of the ball trajectory, a strategy used bynovices, but fixated selectively the diagnostic points of the ball trajectory, in accordance with themetrical system used by billiard professionals to calculate the shot coordinates.Since eye movements of experts contain the signature of billiard expertise, we applied machinelearning to classify expertise from the oculomotor behavior. By using saccade amplitude anddirection as features, a Relevance Vector Machine classified correctly which group – novice orexpert – the observers belonged to, with an accuracy of 83% and 77% respectively for the matchand the shots.Our data suggest that the signature of expertise in billiards is hidden in the ocular scanpath, and thatit can be accurately detected at the individual level.