full transcript

From the Ted Talk by Rajiv Maheswaran: The math behind basketball's wildest moves

Unscramble the Blue Letters


The coaches want players to take good shots. So if I'm snnadtig near the basket and there's nobody near me, it's a good shot. If I'm standing far away surrounded by defenders, that's generally a bad shot. But we never knew how good "good" was, or how bad "bad" was quantitatively. Until now.

So what we can do, again, using spatiotemporal features, we looked at every shot. We can see: Where is the shot? What's the angle to the basket? Where are the defenders standing? What are their distances? What are their angles? For multiple defenders, we can look at how the player's mviong and predict the shot type. We can look at all their velocities and we can build a model that pdrtiecs what is the llkooeihid that this shot would go in under these circumstances? So why is this important? We can take something that was shooting, which was one thing before, and turn it into two things: the qlatiuy of the shot and the quality of the shooter. So here's a bubble carht, because what's TED without a bubble chart?

Open Cloze


The coaches want players to take good shots. So if I'm ________ near the basket and there's nobody near me, it's a good shot. If I'm standing far away surrounded by defenders, that's generally a bad shot. But we never knew how good "good" was, or how bad "bad" was quantitatively. Until now.

So what we can do, again, using spatiotemporal features, we looked at every shot. We can see: Where is the shot? What's the angle to the basket? Where are the defenders standing? What are their distances? What are their angles? For multiple defenders, we can look at how the player's ______ and predict the shot type. We can look at all their velocities and we can build a model that ________ what is the __________ that this shot would go in under these circumstances? So why is this important? We can take something that was shooting, which was one thing before, and turn it into two things: the _______ of the shot and the quality of the shooter. So here's a bubble _____, because what's TED without a bubble chart?

Solution


  1. standing
  2. quality
  3. predicts
  4. chart
  5. moving
  6. likelihood

Original Text


The coaches want players to take good shots. So if I'm standing near the basket and there's nobody near me, it's a good shot. If I'm standing far away surrounded by defenders, that's generally a bad shot. But we never knew how good "good" was, or how bad "bad" was quantitatively. Until now.

So what we can do, again, using spatiotemporal features, we looked at every shot. We can see: Where is the shot? What's the angle to the basket? Where are the defenders standing? What are their distances? What are their angles? For multiple defenders, we can look at how the player's moving and predict the shot type. We can look at all their velocities and we can build a model that predicts what is the likelihood that this shot would go in under these circumstances? So why is this important? We can take something that was shooting, which was one thing before, and turn it into two things: the quality of the shot and the quality of the shooter. So here's a bubble chart, because what's TED without a bubble chart?

Frequently Occurring Word Combinations


ngrams of length 2

collocation frequency
moving dots 4
seconds left 3
guy guarding 2
good shots 2
shot probability 2
ray allen 2


Important Words


  1. angle
  2. angles
  3. bad
  4. basket
  5. bubble
  6. build
  7. chart
  8. circumstances
  9. coaches
  10. defenders
  11. distances
  12. features
  13. generally
  14. good
  15. important
  16. knew
  17. likelihood
  18. looked
  19. model
  20. moving
  21. multiple
  22. players
  23. predict
  24. predicts
  25. quality
  26. quantitatively
  27. shooter
  28. shooting
  29. shot
  30. shots
  31. spatiotemporal
  32. standing
  33. surrounded
  34. ted
  35. turn
  36. type
  37. velocities