Baseball Pitch Prediction using Machine Learning
This student came to Polygence having multiple years of coding experience and had already completed a short AI-ML bootcamp. He decided to take on a sports analytics project that would let him use the ML algorithms he had been exposed to. Looking at a three year dataset from 2015-2018, with hundreds of thousands of entries, he created several machine learning models and a Shiny application that allows users to predict the next pitch of a baseball game given the current game scenario.
His research culminated in a Towards Data Science publication on Medium, in addition to developing a GitHub repository and Shiny App Pitch Predictor.Article in Towards Data Science
Working with Polygence and Ben was great. He was super supportive and helped a lot, especially when I ran into errors that were very uncommon, and I had no idea how to fix them. Working with a mentor was a great experience and really helped me in terms of learning and progressed my abilities faster than any other way. Ben was able to balance helping me, without doing everything for me, allowing me to learn a lot and truly understand what to do.
With Polygence you actually have these one-on-one relationships which is unbelievably different from, and in most cases unbelievably more valuable than sitting in a classroom with an expert at the front of the room. In those scenarios, the experts not talking just to you — that expert is talking to 30 students at once or broadcasting to tens of thousands of people. And so if you have a question or if you want to build a relationship that doesn't get integrated at all. You're just a passive consumer and you have no influence over what's happening, which is totally the opposite of Polygence — the mentor is adapting and it's this beautiful relationship where both people are adapting to one another. Students just get so much further; I think that's an incredibly valuable and unique aspect of Polygence.
Play with the pitch predictor