This summer, StatsBomb is celebrating a special anniversary: 10 years since the site was formed and the first blog post was published.
A decade ago, the football analytics community was nascent, with a handful of prolific analysts experimenting with whatever football data they could get their hands on – which wasn’t a lot. But with every new blog post, a new analyst would be inspired, they'd write a new blog post... and so the community grew.
Ted (Knutson, now CEO of StatsBomb) created StatsBomb.com to house his own writing, but mostly to act as a centralised hub to amplify the work of the early analysts and researchers (for more on that you can read Ted’s 10 Years of StatsBomb blog post). Ten years on, we’ve spoken to some of those early contributors and will be sharing those conversations in a succession of articles that we’re calling the StatsBomb Originals series.
A warm welcome back to Marek Kwiatkowski.
Marek (@statlurker) was a prominent member of the early analytics community. He was a long-time collaborator with StatsBomb CEO Ted Knutson, working together at Brentford FC and FC Midtjylland, and had a key role in a lot of the metrics and design choices used by StatsBomb in the early days, including possession-adjusted defensive metrics and the StatsBomb shot maps. Marek is perhaps best known for his statistical modelling approach to football analytics, with a particular focus on player recruitment and team strength modelling, but some of his most revered work was actually his thoughtful evaluations and foresight of where football analytics should go next.
Here’s Marek.
What was the first thing you worked on as an analyst? Do you remember your first “analytics experiment” or lightbulb moment?
Marek Kwiatkowski (MK): The first thing I did that made sense was the descriptive analysis of midfielder passing patterns for the inaugural Opta Forum in 2014, but I was fully sold on analytics before then.
What has been your favourite piece to write or read on StatsBomb?
MK: No single article comes to mind.
[Editor's Note: Marek's Towards A New Kind of Analytics article received overwhelmingly positive feedback when published, as did his A Toolbox For Football Analytics and Quantifying Finishing Skill articles]
Whose work did you read early on? Where did you read this early work?
MK: I read Colin Trainor, Ben Pugsley, James Yorke, Will Gurpinar-Morgan, Martin Eastwood, Thom Lawrence, James Grayson, Ted Knutson, Bobby Gardiner, Devin Pleuler, Paul Riley, Dan Altman, Mark Taylor, Garry Gelade... mostly on StatsBomb and personal blogs. And on Twitter, of course. Twitter was all-important in the early days.
Do you remember any particular articles that inspired you? Ideas or metrics or research?
MK: I was impressed by Colin Trainor's work. Around 2013 or so, he would write a groundbreaking article every month. He had it clear what he was analysing and why, and would take the shortest path to the answer. He left a large imprint on football analytics and should be better known today than he is.
Are there any metrics/frameworks from the “early days” that you still use in your work now?
MK: There is still some value in mixed-effects models. Otherwise no.
Do you remember any particularly bad analytically-driven takes you had in the past, or work that you would approach differently knowing what you know now?
MK: Many of my old models could be improved on from the technical point of view.
Is there any piece of work that you're particularly proud of?
MK: I am proud of my algorithm to synchronise event and tracking data, because it solves an important problem in an elegant way.
Where has your analytics work taken you and your career?
MK: Thanks to football data I became an applied statistician. I have had many fantastic opportunities over the years, consulting for football clubs but in other fields too.
How would you rate the progression of analytics in the last 10 years, in terms of both research and application?
MK: The adoption of analytics over the last decade has been incredible. It's harder to judge the progress of research, because much of it is proprietary.
What are you most excited about in the future for football analytics?
MK: We need to learn how to separate collective and individual contributions to performance. Wider availability of off-the-ball data and development of scalable Bayesian methods are reasons to be hopeful.
Our sincere thanks to Marek for giving up his time to share his experiences with us. You can find him on Twitter @statlurker or through his website.
We’ll be back next week with more from the StatsBomb Originals series.
