COVID19 Project

THE PROBLEM
PREDICTING THE NEXT PITCH A BASEBALL PITCHER WILL THROW
Pro baseball players have about 0.4 seconds to react after the pitcher throws a pitch. Thus, they study game film to figure out what opposing pitchers will do before they do it. When does he throw a curveball? How about a fastball? The best batters are pretty good at this. But no batter is better at this than a computer that knows everything about every pitch the pitcher has ever thrown, and uses that data to predict what he's about to do next.

THE SOLUTION
MACHINE LEARNING IN PSEUDO-REAL TIME
Using Python and an storing  in Amazon Web Services S3 bucket, we built a  machine learning model that redicts.....Across a random sample of 50 pitchers, we saw an average improvement of about 5 percentage points beyond predicting the pitcher's most common pitch type every time. However, there was high variance: some pitchers were much more predictable than others. For some, we saw a bump of 15 percentage points on average. The algorithms do even better if you narrow the algorithm to certain game situations in which patterns emerge more clearly. Finally, we hooked the algorithm up to Twitter, so that the algorithm can watch a game and make predictions as the game progresses.

RESULTS(Insert screenshots as needed)

 

PROJECT WEBSITE
For more details, check out the project's website here.

Follow me

© 2023 by Andrea Hobby.
Proudly created with Wix.com

 

  • LinkedIn
  • Twitter