Hi Chris, first of all best of luck with the project, I'm a lifelong supporter so I hope the work you guys are doing will help us get to that 14th title soon!
I also work in IT, albeit in a different field, mostly with Kubernetes clusters, DevOps tools and private clouds. Is your team working with these technologies, does Arsenal have some separate team for this sort of infrastructure-related work? I won't lie, from time to time I check Arsenal job postings but I never once saw anything related to the infra, which is why I'm asking.
Hey Chris. This is such an incredible opportunity and great to hear folks like you are spearheading the charge. I’ve a friend who’s leading AI at Real Madrid and it’s fascinating to hear what they’re trying to do (without him revealing the secret sauce to me!)
Does your team and department taking of analytics primarily on the footballing side? Like player performance? How does your teams work typically get incorporated and what does the day to day look like? Do you manage your own tech stack as well?
> Does your team and department taking of analytics primarily on the footballing side? Like player performance?
Yes, we work primarily on the footballing side and across the spectrum in that space: Player/team performance for the men's first team, women's first team, and boys academy age groups U16 and up, player recruitment / squad planning, etc.
> How does your teams work typically get incorporated
We produce a mix of interactive tools, regular static reports (e.g. opposition analysis, post-match analysis, etc.), and live dashboards that come from specific stakeholder requests such as coaching staff or execs, or that we build proactively to address a specific football-related question.
> what does the day to day look like?
It really varies from day to day and role to role within the team. A data engineer might be adding another data provider to an entity resolution ETL pipeline, a research scientist might be incorporating feedback from first team coaching staff into a work-in-progress model, a data analyst might be putting together an in-depth opposition analysis report for an upcoming match, and an operations analyst might be helping train operators on a new data labeling task.
> Do you manage your own tech stack as well?
We do manage most of our tech stack, although we get a lot of support on front-end from a great sister team in the IT dept.
There definitely is hope for AI aiding with the less subjective elements of refereeing, such as offside, ball out of bounds, keeper moving off of line before a penalty is taken, etc.
It has already had a big impact for ball crossing the goal line judgments if you put computer vision in the broader AI category (e.g. Hawkeye in the PL)
I read the headlines and was surprised to see the replay of the red card afterwards. There's no intention to harm but he went studs first on the calf and then all the way down to the foot. Red card is harsh but imho not a blatant error. You can't go studs first.
There's a pattern of referees giving unreasonable red cards to Arsenal, and those same referees getting lavish trips to the Dubai, which is where the owners of our title race rivals for 2 previous seasons are located.
It's a similar conflict of interest, if not outright corruption as Justice Clarence Thomas getting free all expenses paid fishing trips and other goodies from a billionaire who wants to influence Supreme Court decisions.
Hmm, well the super secret stuff we’re working on comes directly to mind, but if I set that aside, boring entity resolution is actually a big pain point.
Regardless of their sophistication, 3rd party data products in football tend to rely on manually collected and maintained player metadata. It can be unreliable. If I could reliably have a durable unique ID for every player, manager, and team in world football along with reliable timestamps for every moment each said player entered and left play, that would be pretty great. When joining together disparate data sources, discrepancies in things this simple cause all sorts of pain downstream.
This works really well until you're dealing with potato quality video, weird fonts, and shirts plastered with ads, or even pretty good quality video and white shirts with white lettering (https://www.arsenal.com/news/how-volunteer-part-no-more-red).
Aside from 3rd party data, we contract with a nonprofit in Laos where operators collect event data for us (~2000 data points per match) across roughly a dozen leagues worldwide.
