【Moneyball】
"People in both fields operate with beliefs and biases. To the extent you can eliminate both and replace them with data, you gain a clear advantage." -- Michael Lewis, Moneyball.
When sabermetrics, the empirical analysis of baseball (statistics) that measure in-game activity, first came about, there was a lot of resistance from coaches and players to stick to the traditional way of picking players and plays. As we continue to find arguments for a more data-driven approach in all industries, we can see things like AI starting to pervade all facets of life, including sports.
The NBA has been using machine learning and AI for a while to track every game, with cameras that keep a record of every game and player to collect so much more information than before. As the cameras collect this information, they are able to train their algorithms on the data set to recognize patterns in players and plays: "The resulting software can then go through all of the tracking data, identify and label every player and play, and create a database of searchable, annotated and animated diagrams of moving dots that represent each player."
Ultimately, all sports is still a game played by humans, so we can't lose that human touch -- the random play that no machine could have predicted. However, combined with AI, sports can become that much more interesting, competitive, and fun. May the best team win!
If you're working on an AI- or Blockchain-related startup, apply now to be a part of AppWorks #18! http://bit.ly/2ENOBjw
OP: Natalie Feng Lin
