Sports Analytics
Which players could help Fulham overcome their major flaws?
Some days ago, I used to be fortunate to find a way to take part in a football analytics hackathon that was organized by xfb Analytics[1], Transfermarkt[2], and Football Forum Hungary[3].
As we recently received permissions to share our work, I made a decision to write down a blog post concerning the approach I used.
The goal was to select a Premier League team, analyze their playing style, highlight two flaws, and prepare two lists of 5 players each that would help the team improve. The premise was that we needed to look to fill two different positions (hence the “two lists of 5 players each”).
Then, from those two lists, we had to select the highest goal in each and further explain why they were one of the best fit for his or her respective positions.
The outcome needed to be realistic and the sum of each players’ prices needed to be below 60M (we got their Transfermarkt valuations).
Now that you already know what it was about, I would like to discuss my approach. I’m a knowledge science guy who loves football so I needed to perform some form of technical evaluation or modeling with Python.
Here’s how I’ll structure this post:
- Introductory Evaluation
- Player Clustering
- Picking the Defensive Midfielder
- Picking the Striker
- Conclusions
Have in mind that, as said, this was a hackathon. The time to do it was limited and the resources were quite scarce. With proper time and enough data, the outcomes would have been even higher.
Introductory Evaluation
Relating to player recruitment, data might be our greatest friend. It doesn’t guarantee anything in the long run, however it allows us to know the past and present of a player in a purely objective manner: his playing style, his profile, benefits and downsides…
For that reason, I wanted this project to be 90% based on data, and let common sense reign over the remaining 10%.