Cash Moneyball

Inspiration

We wanted to help the Georgia Tech Softball Team win more games and we wanted to help the softball coach and staff do tedious work. Coach Morales, head coach of the GT Softball team, would manually graph scouting reports for opposing teams, taking up to six-hours per series. While there are other analytic sheets available, they have an excess of information; it’s simply too much to be useful in game. By creating this project, we solve both problems of information overload, and the time consuming nature of scouting reports.

What it does

Our program takes in a team name and the team url on the NCAA site and returns a pdf visual scouting report with a page of information on each of the opposing teams players.

How we built it

We used Python and many other libraries to scrape, parse, and present our data.

Challenges we ran into

When parsing through the play by play data, we noticed that there were many different terms for the same thing. One team will write short stop as ‘ss’, while others will spell it out. All of these different cases made it difficult to ascertain accurate data, but through enough testing, we were able to cover all of the edge cases.

Accomplishments that we're proud of

We were able to create a scouting report, resembling the ones that the softball team makes in 6 hours, within a few mins.

What we learned

While it’s important to have strong data analytics, it is just as important to deliver this information in a way that is easy to understand, yet impactful. If the end-product is difficult to interpret, it will simply not be used.

What's next for Cash Moneyball

This specific program can be used by any and all softball teams, as long as they have stats on the NCAA webpage. With a few quick fixes, this can be easily implemented for professional teams in both the major and minor leagues.

Built With

• beautiful-soup
• numpy
• pandas
• pyqt
• python
• reportlab
• urllib