⚾ Minor to Major League Forecaster ⚾
Explore the docs »
Visit the Site! » Sorry, Website is Down!
View Demo
·
Report Bug
·
Request Feature
Table of Contents
I have a few passions, but at the top of my list are Machine Learning and Baseball. So when I saw this hackathon pop up with the prospecting challenge, I knew exactly what I was going to do. I was going to try and predict the future.
Billy feeds in all of the major and minor league data I could get ahold of from baseball reference and uses it to train a machine learning model to predict how a minor leaguer will perform in the bigs.
First I started in R to get the baseball reference data for the majors and minors. Then it was off to the Google Vertex Workstation to create the model to learn from the data. After that was complete the process of deploying and endpoint to that model began. Finally once everything was set up I could focus on creating and hosting a webpage to access predictions from the model!
Web development is not my bread and butter so there was a lot of throwing my head against the wall attempting to get everything to integrate cleanly together. I also had to rapidly learn how to host a server and had a few incredibly late nights near the end.
I truly believe that every part of this project was an immensely helpful learning experience, I had never used almost any of the tools other than tensorflow before and it opened my eyes to so many great platforms and frameworks that will become regular parts of my workflow.
Next steps is to conglomerate as much data as possible to try and get even more accurate predictions. Perhaps working in conjunction with the MLB could make this possible!
This section should list any major frameworks/libraries used to bootstrap your project. Leave any add-ons/plugins for the acknowledgements section. Here are a few examples.
- R
- Python
- JS
- Google Vertex
- Heroku
- Tensorflow
Simply visit the hosted webpage and type in BA, OBP, & SLG statistics and peer into the future!
Distributed under the MIT License. See LICENSE for more information.
Riley Roberts - Linkedin
Project Link: https://github.com/syanification/Billy
This project would NOT have been possible without these fantastic resources so check them out!