How long do actions echo? ⚽️🔊
🇮🇹 A few weeks ago I was back at the #MLSA workshop, held during ECML/PKDD in Napoli.
🔜 I presented our latest study on possession value frameworks, where we analyse the “near future” over which the effect of an action is measured.
𝐀𝐧𝐚𝐥𝐲𝐭𝐢𝐜𝐬 𝐂𝐮𝐩 𝟐.𝟎 𝐢𝐬 𝐡𝐞𝐫𝐞. 🇪🇺🇺🇸
Following the success of the first edition, PySport and @skillcorner.bsky.social are inviting the analytics community to work with open-source 𝐟𝐨𝐨𝐭𝐛𝐚𝐥𝐥 𝐝𝐚𝐭𝐚 (including body pose data) and 𝐛𝐚𝐬𝐤𝐞𝐭𝐛𝐚𝐥𝐥 𝐝𝐚𝐭𝐚 to turn new ideas into open-source projects with real value.
In the last chapter of her PhD thesis Lotte Bransen looked at penalty kicks. Several interesting things emerged.
A simulation study indicated slightly higher save percentage if the goalkeeper did not always align directly in the center of the goal.
1/5
⚽➡️🧠 It’s a only small step from soccer analytics to Parkinson’s research…
Over the past years, I collaborated on a project to improve how we understand Parkinson’s disease. It’s now published in Nature Communications: www.nature.com/articles/s41...
Curious how soccer fits into this? Read on 👇
𝗪𝗵𝘆 𝗶𝘀 𝘁𝗵𝗮𝘁 𝗶𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴?
These findings show that the disease is better understood as a collection of related conditions. It explains why one treatment does not work for all patients, and brings personalized treatment for Parkinson’s a step closer.
This was a collaboration with @jessejdavis.bsky.social and many others across VIB and KU Leuven. I only played a small part.
Still, it’s pretty amazing to see our sports analytics research translate into something with real societal impact.
Read the full paper here:
www.nature.com/articles/s41...
⚽➡️🧠 It’s a only small step from soccer analytics to Parkinson’s research…
Over the past years, I collaborated on a project to improve how we understand Parkinson’s disease. It’s now published in Nature Communications: www.nature.com/articles/s41...
Curious how soccer fits into this? Read on 👇
3️⃣
Each fly is then described as a weighted mix of these patterns.
These weights let us compare flies, cluster them, and detect subtle behavioral differences linked to genetic mutations.
𝗪𝗵𝗮𝘁 𝗱𝗶𝗱 𝘄𝗲 𝗳𝗶𝗻𝗱?
While Parkinson's is typically considered as one disease defined by shared symptoms, we found two main groups and five subgroups of Parkinsonism—showing that it can be caused by mutations in many different genes.
⚽➡️🧠 It’s a only small step from soccer analytics to Parkinson’s research…
Over the past years, I collaborated on a project to improve how we understand Parkinson’s disease. It’s now published in Nature Communications: www.nature.com/articles/s41...
Curious how soccer fits into this? Read on 👇
1️⃣
We convert each fly’s (x,y)-movement into vectors that capture when different behaviors occur (sleeping, eating, walking) throughout the day.
Each fly → one vector per behavior.
2️⃣
We stack these into matrices and apply NMF.
This automatically uncovers shared behavioral patterns (i.e., “behavioral building blocks”) across flies such as waking up early or being restless at night.
⚽➡️🧠 It’s a only small step from soccer analytics to Parkinson’s research…
Over the past years, I collaborated on a project to improve how we understand Parkinson’s disease. It’s now published in Nature Communications: www.nature.com/articles/s41...
Curious how soccer fits into this? Read on 👇
Back in 2019, Tom Decroos introduced Player Vectors — a method using Non-Negative Matrix Factorization (NMF) to capture soccer players’ playing styles.
In short:
Players are represented by where they act on the pitch and what they do there.
More here:
dtai.cs.kuleuven.be/sports/blog/...
Our 2026 World Cup predictions are live! 🔮
🇪🇸 Spain (24%) is the clear favourite, followed by 🇦🇷 Argentina (17%), 🇫🇷 France (11%), 🏴 England (7%) and 🇧🇷 Brazil (5%).
Explore every team’s path to the final in our interactive 👇
w/ @jessejdavis.bsky.socialdtai.cs.kuleuven.be/sports/world...
If you are interested in Bayesian analysis and the Bayesian framework in general (which you should imo) I've put together an open course on coursera. Check it out here: www.coursera.org/specializati...#Bayesian#MachineLearning#DataScience
What if you could simply “prompt” a model with a few shots and get accurate xG predictions?
#TabPFN is making waves on academic benchmarks. We tested how it handles a real-world sports analytics problem.
w/ Timo Martens & @jessejdavis.bsky.socialdtai.cs.kuleuven.be/sports/blog/...
⏳ The submission deadline for our MLSA workshop is coming up soon: June 5, 2026 (just two weeks away)!
Don’t miss the chance to share your ongoing research ideas or recent work on Sports+AI!
Our Workshop on Machine Learning and Data Mining for Sports Analytics (MLSA) will happen again as part of @ecmlpkdd.org!
📅 7 or 11 Sept 2026
📍 Naples, Italy
📝 Submissions due 5 June 2026
\w @hugoriosneto.bsky.social@azimmermdm.bsky.social & Maaike Van Roy
dtai.cs.kuleuven.be/events/MLSA26/
Don't miss the deadline for the LISS Football Analytics Symposium! Here are 3 reasons to get that abstract in 👇
1️⃣ Make an impact: Present your work directly to club analysts
2️⃣ Low effort: 2-page abstract (published research welcome!)
3️⃣ Learn from 4 of my favourite speakers on soccer analytics
⚽Call for Abstracts ⚽
The abstract submission for the Leuven Institute of Sport Science’s #FootballAnalytics Symposium closes this Thursday, Feb 26 @ 17:00 CET
The symposium is on April 23rd. Speakers include @unravelsports.bsky.social and Pascal Bauer (DfB)
www.kuleuven.be/liss/events/...
We’re recruiting for a Data Engineer to join our Research team at Liverpool FC. In my (perhaps biased) view, it’s a great opportunity to join an excellent team, work at the forefront of sports analytics, and have a tangible impact.
www.linkedin.com/posts/conorq...
⚽Event Announcement⚽
Leuven Institute of Sport Science’s #FootballAnalytics Symposium will take place on April 23!
Current invited speakers are Prof. Pascal Bauer (DFB, USaarland) and @unravelsports.bsky.social
Abstract submission closes on Feb 26 @ 17:00 CET
www.kuleuven.be/liss/events/...
It’s that time of year again: proposals are now being accepted to present at Opta Forum 2026, which is taking place in London at the end of March.
If you are interested in taking part, the submission deadline is 9th February. Full details can be found ⬇️
www.statsperform.com/resource/opt...
Continuing the tradition, I have compiled an end-of-year overview of the soccer analytics content that I liked the most in 2025. This edition includes pointers to about 200 resources, including research papers, blog posts, news articles, podcasts, and webinars.
janvanhaaren.be/posts/soccer...
Can we measure the ability to block dangerous passes in soccer? ⛔️⚽️
We recently presented our latest research paper "Quantifying Off-Ball Defensive Impact through Cover Shadows" at the Hudl Performance Insights 2025 Conference:
📺 youtu.be/kf6far1Zst8?...
📝 static.hudl.com/craft/perfor...
We're expanding the Club Brugge Football Data Science team. As our Football Data Scientist, you'll work with one of the most advanced analytics infrastructures in football to help management, scouting, and analysis staff turn data into better decisions.
jobs.clubbrugge.be/en/football-data-scientist
IMPECT released a season of public event data! ⚽
There’s already plenty of event data out there — so why care? Because IMPECT’s data adds some really cool and unique features, such as their Packing Zones.
And with the new kloppy v3.18 release, it's really easy to get started with this dataset.
🚀 𝐁𝐢𝐠 𝐧𝐞𝐰𝐬 𝐟𝐨𝐫 𝐭𝐡𝐞 𝐟𝐨𝐨𝐭𝐛𝐚𝐥𝐥 𝐚𝐧𝐚𝐥𝐲𝐭𝐢𝐜𝐬 𝐜𝐨𝐦𝐦𝐮𝐧𝐢𝐭𝐲!
We are thrilled to announce the release of our 𝐨𝐩𝐞𝐧 𝐝𝐚𝐭𝐚 – the 𝐦𝐨𝐬𝐭 𝐜𝐨𝐧𝐭𝐞𝐱𝐭𝐮𝐚𝐥𝐢𝐳𝐞𝐝 𝐞𝐯𝐞𝐧𝐭 𝐝𝐚𝐭𝐚𝐬𝐞𝐭 𝐢𝐧 𝐟𝐨𝐨𝐭𝐛𝐚𝐥𝐥, covering the 2023/24 𝐁𝐮𝐧𝐝𝐞𝐬𝐥𝐢𝐠𝐚 𝐬𝐞𝐚𝐬𝐨𝐧, including Bayer 04 Leverkusen’s historic invincible campaign.
We’re excited to launch the 𝐒𝐤𝐢𝐥𝐥𝐂𝐨𝐫𝐧𝐞𝐫 𝐗 𝐏𝐲𝐒𝐩𝐨𝐫𝐭 𝐀𝐧𝐚𝐥𝐲𝐭𝐢𝐜𝐬 𝐂𝐮𝐩 - a hackathon-style challenge that will bring together the community to collaborate, compete, and innovate using open-source SkillCorner data.
👉 Sign up pysport.org/analytics-cup
Before an app launches, it undergoes usability testing. Why shouldn't an advanced sports metric?
In our latest blog, we propose 4 criteria:
1️⃣ Trustworthy
2️⃣ Novel
3️⃣ Intuitive
4️⃣ Useful
Then, we put VAEP to the test...
\w @jessejdavis.bsky.social & Maaike Van Roy
dtai.cs.kuleuven.be/sports/blog/...
Before an app launches, it undergoes usability testing. Why shouldn't an advanced sports metric?
In our latest blog, we propose 4 criteria:
1️⃣ Trustworthy
2️⃣ Novel
3️⃣ Intuitive
4️⃣ Useful
Then, we put VAEP to the test...
\w @jessejdavis.bsky.social & Maaike Van Roy
dtai.cs.kuleuven.be/sports/blog/...
We can use xG to compute post-hoc win-draw-loss probabilities.
Our new blogpost shows MCMC's estimates of these probabilities are unstable, computing them exactly is faster than approximating them, and MCMC's runtime strongly depends on its implementation.
dtai.cs.kuleuven.be/sports/blog/...
Looking forward to the #MLSA25 workshop next week at @ecmlpkdd.org! We'll have some exciting research on soccer, ultimate frisbee, basketball and table tennis. ⚽🥏🏀🏓
Want a sneak peek? The papers are already available on the workshop website 👇
The Carnegie Mellon Sports Analytics Conference is an annual event dedicated to highlighting the latest sports research from the statistics and data science community. Registration for the 2025 CMSAConference is open.
🔗 www.cmsaconference.com
“What if, when the opposition has 11 players behind the ball, a centre-back decided it was more worthwhile to ‘kick for touch’ rather than attempt to play through midfield?”
Oh boy do I have a research presentation for you
Excited to announce a new paper together with @sigridolthof.bsky.social entitled "Perspectives on data analytics for gaining a competitive advantage in football: computational approaches to tactics".
This is a synthesis article that has 3 key objectives
www.tandfonline.com/doi/epdf/10....
1 / 4
🔷 𝐏𝐲𝐒𝐩𝐨𝐫𝐭 𝐗 𝐏𝐲𝐃𝐚𝐭𝐚 𝐄𝐢𝐧𝐝𝐡𝐨𝐯𝐞𝐧 𝐂𝐚𝐥𝐥 𝐟𝐨𝐫 𝐏𝐫𝐨𝐩𝐨𝐬𝐚𝐥𝐬! 🔶
On December 9th @PyData Eindhoven and @pysport.org will organize 𝐏𝐲𝐃𝐚𝐭𝐚 𝐄𝐢𝐧𝐝𝐡𝐨𝐯𝐞𝐧 𝟐𝟎𝟐𝟓!
𝐌𝐨𝐫𝐞 𝐢𝐧𝐟𝐨: lnkd.in/eBGWKs3V
Your fave women’s footie analytics gals (@cata-bush.bsky.social and myself, ofc) are at it again!
Below is a VAEP inspired breakdown of the Women’s Euros group stages - read to see which players and teams have shown out or bombed (whoops, Netherlands 👀):
open.substack.com/pub/beyondth...
Our Women's Euro 2025 predictions are out! 🔮
Spain 🇪🇸 is our model's favorite to win the title, with Germany 🇩🇪 close behind. Meanwhile, Belgium 🇧🇪 will most likely be eliminated in the group stage.
w\ @jessejdavis.bsky.socialdtai.cs.kuleuven.be/sports/blog/...
Our Women's Euro 2025 predictions are out! 🔮
Spain 🇪🇸 is our model's favorite to win the title, with Germany 🇩🇪 close behind. Meanwhile, Belgium 🇧🇪 will most likely be eliminated in the group stage.
w\ @jessejdavis.bsky.socialdtai.cs.kuleuven.be/sports/blog/...
📊 Our interactive visualization provides detailed odds for each team advancing past the group stage and eventually winning the tournament. We will update the probabilities after each round.
dtai.cs.kuleuven.be/sports/euro2...
Our Women's Euro 2025 predictions are out! 🔮
Spain 🇪🇸 is our model's favorite to win the title, with Germany 🇩🇪 close behind. Meanwhile, Belgium 🇧🇪 will most likely be eliminated in the group stage.
w\ @jessejdavis.bsky.socialdtai.cs.kuleuven.be/sports/blog/...
We estimate each team’s strength based on historical performances using Elo ratings. Then, we run Monte-Carlo simulations to calculate the probability of every team reaching each stage of the tournament.
We're looking for an ML Engineer to join our team at Sportec Solutions. Lots of exciting projects in the pipeline, including ones with skeletal-tracking data. Apply or pass it on to someone who might be interested!
sportec-solutions.jobs.personio.de/job/2151299?...
🚀 Ingestify 0.7.0 is live
Parsing football data with kloppy is fun. The hard bit is fetching raw files and keeping them clean and version-safe.
That’s the gap Ingestify fills.
github.com/PySport/inge...
I strongly believe biomechanical analysis will be the next big leap in sports analytics—and not just for the pros. I got a glimpse by testing the @runeasi.bsky.social sensor (a @dtai-kuleuven.bsky.social spin-off) and wrote about how it helped during my marathon training → runeasi.ai/my-marathon-...
Had the pleasure of attending the Linköping Hockey Analytics Conference this week. Thought “icing” was just for cakes, but somehow they still let me on stage 😅 Loved the welcoming community and saw lots of familiar ideas with huge potential across sports. #LINHAC
I wrote about @jessejdavis.bsky.social, an American computer science professor running an influential soccer analytics research team at an ancient university in Belgium.
Much of the leading data analysis is still being done outside soccer. Why?
@theguardian.comwww.theguardian.com/football/202...