p_robberechts Profile Banner
Pieter Robberechts Profile
Pieter Robberechts

@p_robberechts

Followers
2K
Following
866
Media
40
Statuses
354

PhD student @DTAI_KULeuven, applying Machine Learning on sports data.

Belgium
Joined January 2010
Don't wanna be here? Send us removal request.
@l_cascioli
Lorenzo Cascioli
8 months
๐ŸšจThe third and final blog post in our series on possession value models design decisions๐Ÿ”: Can the features chosen to represent the game state inadvertently bias player ratings? w/ @p_robberechts @jessejdavis1 @lodevantente
Tweet card summary image
dtai.cs.kuleuven.be
Conceptually, possession value approaches such as VAEP, PV, OBV, and g+ are all identical: they estimate the chances of scoring (andโ€ฆ
1
6
13
@p_robberechts
Pieter Robberechts
8 months
The workshop welcomes research on applying ML & data mining to sports โ€” all disciplines, including e-sports. ๐Ÿ“… Monday 15 or Friday 19 September 2025 ๐Ÿ“ Porto, Portugal ๐Ÿ“ Submission info: https://t.co/DTXTrcPNkb Feel free to reach out with any questions!
1
0
3
@p_robberechts
Pieter Robberechts
8 months
After a fantastic run by @JanVanHaaren, @jessejdavis1 and Ulf Brefeld, weโ€™re honored to carry the torch and continue the workshop's legacy! ๐Ÿ”ฅ
2
0
2
@p_robberechts
Pieter Robberechts
8 months
๐Ÿ“ฃ Excited to share that the Workshop on Machine Learning and Data Mining for Sports Analyticsย (MLSA) will be held again this September as part of @ECMLPKDD! w/ @MaaikeVanRoy @hugoriosneto and @azimmerm_dm https://t.co/BCk6GQU3B3
dtai.cs.kuleuven.be
Workshop on Machine Learning and Data Mining for Sports Analytics at ECML/PKDD 2025
1
4
18
@ethanf_17
Ethan
10 months
One of my hobbies is doing some light data science for soccer. Best package in the game is SoccerData. Makes it easy to pull down dataframes of match and season data from the major soccer providers.
2
4
24
@PySportOrg
PySport
1 year
๐ŸŽ„ ๐ค๐ฅ๐จ๐ฉ๐ฉ๐ฒ==๐Ÿ‘.๐Ÿ๐Ÿ”.๐ŸŽ Happy Holidays to the Sports Analytics Community! This release contains some exciting updates, you can find the highlights in this thread. But first, we're really excited that @p_robberechts has officially joined as a maintainer! ๐Ÿ’™
1
2
8
@l_cascioli
Lorenzo Cascioli
1 year
Part 2 in our series on possession value models design decisions๐Ÿ”: How the definition of "near future" has interesting effects on player ratings. It's not about 'better,' but about understanding the nuances. w/ @p_robberechts @jessejdavis1 @lodevantente https://t.co/QGAsvnkh41
Tweet card summary image
dtai.cs.kuleuven.be
Conceptually, possession value approaches such as VAEP, PV, OBV, and g+ are all identical: they estimate the chances of scoring (andโ€ฆ
1
9
20
@p_robberechts
Pieter Robberechts
1 year
I promise there will be some great insights into this blog post series.
@l_cascioli
Lorenzo Cascioli
1 year
We're doing a deep dive into possession value models. While VAEP, g+, PV & OBV are conceptually identical, they make different design choices. First, we look at using (no) goal vs. xG as the target variable. w/@p_robberechts @jessejdavis1 @lodevantente https://t.co/5hyFDrsDDo
0
0
3
@p_robberechts
Pieter Robberechts
1 year
Nothing quite like a 'quick update' turning into a two-day saga of dependency chaos. But hey, ๐—ฑ๐Ÿฏ-๐˜€๐—ผ๐—ฐ๐—ฐ๐—ฒ๐—ฟ is updated for the first time in 4 years! ๐Ÿš€ https://t.co/NjhN1smZgF
2
12
117
@l_cascioli
Lorenzo Cascioli
1 year
Has soccer gone too far in its obsession with keeping possession?โšฝ๏ธ A few weeks ago I presented our latest research paper โ€œBoot It: A Pragmatic Alternative to Build-Up Playโ€ at the #StatsBombConference. ๐Ÿ“ฝ๏ธ https://t.co/9k20mIyYc3 ๐Ÿ“ https://t.co/rS3DXs4XO1 [1/3]
3
4
15
@p_robberechts
Pieter Robberechts
1 year
Attending @ECMLPKDD and interested in sports โšฝ๐Ÿ€๐Ÿˆ? Donโ€™t miss our tutorial on Team Sports Analytics tomorrow! Our goal is to provide an accessible overview of existing work on the use of machine learning in sports. Check out the details here ๐Ÿ‘‰ https://t.co/WmMwCzH7R6
1
6
20
@mr_le_fox
Koen Vossen
1 year
Part of @kloppy_dev 3.15.0 is the ๐˜ข๐˜จ๐˜จ๐˜ณ๐˜ฆ๐˜จ๐˜ข๐˜ต๐˜ฆ method. This allows you to go from dataset to aggregation in a single line. The first one implemented is ๐˜ฎ๐˜ช๐˜ฏ๐˜ถ๐˜ต๐˜ฆ๐˜ด_๐˜ฑ๐˜ญ๐˜ข๐˜บ๐˜ฆ๐˜ฅ. It returns the time a player was on the pitch (including start- and end timestamps).
1
2
9
@p_robberechts
Pieter Robberechts
1 year
At long last, we have a (fingers crossed) bug-free implementation of orientation and pitch dimension transforms in @kloppy_dev!๐Ÿš€โœจ
@PySportOrg
PySport
1 year
๐Ÿš€ ๐ค๐ฅ๐จ๐ฉ๐ฉ๐ฒ==๐Ÿ‘.๐Ÿ๐Ÿ“.๐ŸŽ A new version of kloppy (3.15.0) is now available! This release includes major additions: โœ… DatasetTransformer (to easily transform pitch dimensions) โœ… Minutes Played Aggregator โœ… Time Based Positions โœ… Improved Orientation
0
4
13
@mr_le_fox
Koen Vossen
1 year
Where do you normally store large assets required for automated tests? Should it be part of the repository? Those assets can be several GB so donโ€™t want to download those on every single run. Oh, and the assets are private and access should require some sort of authentication.
3
1
0
@jessejdavis1
Jesse Davis
1 year
Curious about the favorites for #CopaAmรจrica2024? our projections are below with home advantage for the US. w/@p_robberechts
0
3
11
@p_robberechts
Pieter Robberechts
1 year
๐ŸŸ๏ธ With 51 matches ahead, our computer model has a standout #euro2024 favoriteโ€”France๐Ÿ‡ซ๐Ÿ‡ท at 26%. Other top contenders include: ๐Ÿ‡ฉ๐Ÿ‡ช16%, ๐Ÿด๓ ง๓ ข๓ ฅ๓ ฎ๓ ง๓ ฟ15%, ๐Ÿ‡ต๐Ÿ‡น11%, ๐Ÿ‡ช๐Ÿ‡ธ10%. Our interactive visualization provides detailed odds for each team๐Ÿ‘‡(\w @_dnzcn @jessejdavis1 ) https://t.co/UVHjcYiRJK
1
0
14
@p_robberechts
Pieter Robberechts
1 year
A key challenge in developing sports analytics metrics is how to evaluate them. I shared some insights on this topic at the @PySportOrg meetup a few months ago, covering various approaches and lessons learned. A recording of the talk is now available online.
@PySportOrg
PySport
1 year
The videos of our last meetup at the @statsperform office are out on youtube! Presentations by @p_robberechts, @numberstorm and @patricklucey. Thanks @andycoops83 for co-organising this great event! https://t.co/k6CmoPQsTp
0
4
17
@_dnzcn
Deniz Can
1 year
Our projections are back! ๐Ÿ”ฎ We have simulated #euro2024. Our model rates France as the strong favorite with a 26% chance of winning, followed by Germany, England, Portugal, and Spain. w/@p_robberechts @jessejdavis1 https://t.co/V9YIJNSPyI
dtai.cs.kuleuven.be
It is hard to believe, but it is already time for another Euros Football Tournament. So, who are the favorites and dark horses heading intoโ€ฆ
1
5
14
@mplsoccer_dev
mplsoccer_dev
2 years
11. soccerdata (scrape data)
@HenshawAnalysis
Liam Henshaw
2 years
Python Packages to explore for football analytics: 1. mplsoccer (football viz) 2. statsbombpy (statsbomb package) 3. openai (AI) 4. numpy (math) 5. scikit-learn (machine learning) 6. matplotlib (data viz) 7. bs4 (web scraping) 8. requests (web scraping) 19 pandas (data cleaning)
0
3
77