AI predict best batters in baseball

The research comes from the Duke University Medical Center. With the study, computer scientists discovered that baseball players with higher scores on computer-based vision and motor tasks went on to have better on-base percentages. In addition, these players had more walks and fewer strikeouts ('plate discipline') compared with those who did not take part in similar tests. Artificial intelligence was used to make the predictions, drawing inferences from Bayesian hierarchical latent variable models. The inference is that the baseball scouts of tomorrow who are on the look out for a consistent, conscientious hitter may find as many clues by assessing data gathered from how the player completes task in front of a computer screen as they would from watching the player exhibit his or her sporting prowess on the field.