Sarah Rudd: The difference between Twitter analytics & club analytics
Written by Simon Austin — September 4, 2023
TWITTER is full of amateur football analysts - and some go on to become pros.
One of those is Sarah Rudd, who was Vice President of Analytics and Software Development at Arsenal for almost a decade and who now runs her own analytics consultancy, src ftbl, along with husband Ravi Ramineni.
“A lot of people, myself included, got their breaks in the industry because of Twitter,” Rudd told Episode #55 of the TGG Podcast, which you can listen to below. “Mine less directly related to having a huge following, but certainly the interactions I had on Twitter were very helpful in my career.”
Several others have been talent-spotted on the platform by clubs and we’ll talk about some of those later on in this piece.
So what are the main differences between being a Twitter and club analyst? And would what’s popular on the platform cut the mustard in the pro game?
“I see a lot of bad stuff out there still, where people are assuming a number means something when it doesn’t,” Rudd admitted. “We have to nail the basics still.”
There are also big differences in terms of audience and objectives.
“Twitter is for fun, Twitter is entertainment for a lot of people,” Rudd explained. “People like to have debates about who is better or why is this team good and why does this team fall off a cliff.
“Some of that stuff is not necessarily actionable or how a club would approach it, so there is a huge gulf. There is also that huge gulf of what is happening in the public sphere versus what is going on behind the scenes internally at a club, where you are thinking about these things full-time rather than just on a Saturday or in your evenings.
“Twelve years ago, when I got hired into StatDNA (the American analytics company that was acquired by Arsenal in December 2012), I was absolutely blown away at what they were already doing.
“For example they already had a pass value model, they just implemented it in a different way.”
JOURNEY INTO CLUB ANALYTICS
Rudd’s journey to Arsenal and beyond is interesting and informative for aspiring club analysts.
“I knew I wanted to get into football analytics, but football analytics didn’t really exist back then,” admitted the American, who studied computer science at Columbia Engineering in New York.
A chance meeting with Mike Forde, then Director of Football Operations at Chelsea, made a big impression.
"I had the pleasure of chatting with Mike Forde at one of the early MIT Sloan Sports Analytics Conferences and explained my situation and what I wanted to do," Rudd said.
“He gave me the advice, ‘Anybody can say they can analyse football data, but what football clubs really want is for somebody to show them what they can do.’”
A year later, at the same conference, fledgling analytics firm StatDNA ran a research paper competition. They provided one season's worth of data from the Brazilian league and invited aspiring data scientists to do their best (or worst).
“I thought, ‘This is the opportunity I’ve been looking for, where I can really show clubs what I can do,’" Rudd recalled. "I took the data and built a Markov Chain Model, looking at what’s the value of the situation the player is in currently and where they moved the ball.
“Is the team more likely to score from that situation, or less likely? You can assign numbers to that, so how much did they increase the probability of scoring or not.
“That was how I got my start and from there I got to present at NESSIS (New England Symposium on Statistics in Sports) and got to chat with Jaeson Rosenfeld (founder and CEO of StatDNA) and he decided to offer me a job. That’s how my story comes full circle I guess.
“Why that paper resonated with people is it’s something that’s quite useful in recruitment. I was thinking, 'If I worked inside a club, what are the sorts of things I would want to know to make these decisions?'”
CREATING YOUR OWN METRICS
Rudd's model resonated in club football but not on Twitter, which is instructive.
Rudd admitted: “That was my first model but it didn’t have a good name! I don’t even remember what I titled that paper or even if I had a name for that metric but it was something horrendous and terrible. This was me being terrible at personal marketing."
A few years later, a young software engineer called Karun Singh, who was working for an AI firm called GrokStyle in San Francisco, came up with a similar concept and named it Expected Threat (xT). This did get a lot of attention on the internet and on Twitter. Singh is now a Data Scientist with Arsenal.
“Then Karun Singh comes along and names a similar concept Expected Threat and I think people gravitated to that because it made more sense, where you have Expected Goals and then you have Expected Threat," Rudd said.
“The implementation of what he was doing is quite different from what I was doing, but he did a great job naming it. You can go around to people and say ‘Expected Threat’ and people understand what that means.”
Singh was once quite prolific on Twitter, but has been silent on the platform since he joined Arsenal in September 2022. This isn't a criticism - it's just the reality of working for a club.
Jay Socik regularly posted on the hugely popular Blades Analytic account until he was appointed Head of Recruitment Analysis at Luton Town two years ago.
“I decided to step away from social media when I joined Luton,” he explained in an interview with The Athletic last year. “Everything that goes on here has to be confidential and a lot of what I used to post would be seen as IPR (Intellectual Property Rights).
“Basically, I don’t want to share information we are going to use. So, I’m fine with having stepped away from Twitter.”
Rudd experienced the same thing when she was at Arsenal and admitted it made her a little uneasy.
“It’s something I have never been happy with,” she told the TGG Podcast. “Arsenal were quite secretive, they wanted to keep everything in-house. I love chatting with people, I love chatting with young people. I think that’s one of the nice things about my current situation - i can be a little more open.
“I love seeing the work people are doing and maybe provide constructive feedback on some things.”