The pursuit of wisdom in any walk of life quickly reveals that what you think you know is not nearly enough to get you to where you want to go. As I'm starting out in my football journey I challenged myself to reach out to those already working in various roles in football to answer a short list of questions. My goal wasn't to get answers but relevant perspectives on the game within the game.
Here is Andy Rowlinson:
Here is Andy Rowlinson:
How did your first opportunity in football come about?
I got my first opportunity in football as I applied to present at the OptaPro Analytics Forum 2019. The topic was how to use tracking data to analyse set pieces. It was a great opportunity as you get a mentor from a football team.
After the Forum, I released mplsoccer, a football library to make visualisations easier in Python.
What attracted you to media/data/scouting? What’s more intriguing now names or numbers?
I like working with football data because it's unlike other analysis. You can supplement your analysis with real video clips to bring your analysis to life, like this fantastic example from Sancho Quinn. Recruitment is one of the biggest use cases for football analytics so ideally, you'd have both names and numbers.
What type of player fascinates you? What caught your eye?
I love players with flair like Ronaldinho and intelligent players who create space for themselves. It's fascinating how top players talk about scanning the pitch to move and look for space like Xavi and Lampard. Tim Sparv also has a great way of thinking about football and analytics.
What is the biggest misconception you’ve found in this space?
A lot of visualisations use fixed templates, while they are great, I like when they are stripped back to convey a narrative. For example, this tweet by Ted Knutson looks at Messi's free-kicks and identifies a possible sweet spot. It's crudely drawn, but the red box shows you exactly where Messi might be better at taking free-kicks. I like highlighting the key story in the graphic and tweaking the title to match the narrative. If you are interested in sports visualisation you should check out SprawlBall by Kirk Goldsberry.
If you could start over what skill would you build on first?
I recently started over again, moved to Finland and completed a Master's degree. Today I think it helps to keep learning throughout life so you can keep on top of the latest trends. My field, machine learning, moves so quickly that new methods are constantly being published. It's key to have a curious mind and be open to trying new things. For example, transformers were only released in 2017 and are now being used to solve both language (GPT-3) and computer vision tasks.
What is more important domain knowledge or curiosity?
This is a tricky question. The modern analysis techniques, like neural networks, work without domain knowledge. For example, a recent Kaggle competition asked people to identify how many yards an NFL player will gain after receiving a handoff. The winning solution used very little domain knowledge and relied on tech. However, a big part of an analyst's role is to ask the right questions and specifically in sports to help the coaches to improve their team's performance. Curiosity and domain knowledge helps a tonne so you can identify the right questions that if answered improve team performance.
While it's also worth noting that high performing teams are typically more diverse and sports teams should, therefore, contain a range of football and non-football knowledge. For example, Marek Kwiatkowski turned to bioinformatics to solve a common problem of syncing events and tracking data, while Daryl Morey turned to behavioural economics to avoid common biases related to NBA draft recruitment.
What is your favorite sports moment? Why?
My favourite sports moment is Liverpool coming back from 3-0 down to beat AC Milan in the 2005 Champions League Final. I was studying for an exam at university and only started to watch the match a few minutes before the first Liverpool goal. It was an unbelievable come-back and you could feel the mood of the room change from shock to disbelief.
This is also a beautiful sporting moment where Jonny Brownlee sacrifices his potential first place to help his younger brother Alistair over the line.
What coach or player would you give a lifetime contract to? Why?
Edwin van der Sar seems to be doing a great job at Ajax and was a great (ex)-player so I would probably give him a lifetime contract.
What advice would you give to someone wanting to get into this space?
Start doing - it is all about playing around with the data and trying to find interesting insights. There are some fantastic resources to get started:
- Sam Gregory's advice for people wanting to get into football analytics
- Devin Pleuler's analytics handbook
Try and do some unique analysis. Ted Knutson recently said no one had studied Dani Alves in the Messi data archive. So if you did this well it would be shared 
. There also loads of value in contributing to open source tooling. Such as Kloppy or mplsoccer, as you learn a lot by contributing.
Who is your favorite athlete? Why?
Jonah Lomu is my favourite athlete. This guy could run the 100m in 10.7 seconds and unbelievably weighed over 18 stone. In the 1995 Rugby World Cup, he ran into a player so hard that an aspirin manufacturer wanted to use the clip for a commercial. He completely dominated England in the Rugby World Cup semi-final and is one of the few players with their own video game.
What is your favorite quote or saying?
"Therefore do not worry about tomorrow, for tomorrow will worry about itself. Each day has enough trouble of its own."
No comments:
Post a Comment