StatSheetStuffer.com

[rahul @withqwerty]

you down with M.C.P.? yeah you know me
v5 of football-docs mcp is out now. it's a one-line-install mcp server that hands your coding agent real football docs so it stops imagining event types, metric definitions, and coordinate systems. free and open source as always.

a lot has shipped since the last update:
statsbomb: full api + 360 + iq metrics (obv, psxg, xgchain, ppda)
impect: packing, pxt, kpi + score framework, set-pieces
skillcorner: tracking, physical data, off-ball runs
wyscout: rebuilt from v3 + v4 docs + data glossary

15 providers and tools (e.g. @mplsoccer_dev, @kloppy_dev) covered now. bugs, questions, missing anything? let me know!

www: https://t.co/0HLAxg1LNM
repo: https://t.co/ICmZ2DcQCI

[Hudl Statsbomb @Statsbomb]

Introducing Defensive Responsibility (DefR): A New Way To Measure Defensive Output

For years, trying to quantify defensive contributions with event data has been an uphill battle.

Enter DefR, a new model from the Hudl Statsbomb data science team 🔽
https://t.co/3GAeUxizfo

[neil @neilmjohnson]

Free Basketball Pose Data for anyone who might be interested: https://t.co/pOQ5H4vPo0

[Michael Lopez @StatsbyLopez]

Stephanie Kovalchik (@StatsOnTheT) has a new book out with history of many sports analytics stories/people https://t.co/GIuhN3vtIT

[Noah Basketball @noahbasketball]

We have tracked hundreds of millions of shots and cracked the equation revealing the perfect metrics of a shot!

On each shot we measured the arc, depth, and left/right positioning and our research shows that 𝘀����𝗼𝗼𝘁𝗲𝗿𝘀 𝗰𝗮𝗻 𝗺𝗮𝘅𝗶𝗺𝗶𝘇𝗲 𝘁𝗵𝗲𝗶𝗿 𝗺𝗮𝗸𝗲 𝗽𝗲𝗿𝗰𝗲𝗻𝘁𝗮𝗴𝗲 𝗯𝘆 𝘀𝗵𝗼𝗼𝘁𝗶𝗻𝗴 𝘄𝗶𝘁𝗵 𝗮𝗻 𝗲𝗻𝘁𝗿𝘆 𝗮𝗻𝗴𝗹𝗲 𝗼𝗳 𝟰𝟱°

[Ron Yurko @Stat_Ron]

Strongly recommend checking out a new #sportsanalytics book by (one of the best in the field) Stephanie Kovalchik (@StatsOnTheT ) called - 'Out of Left Field: Improbable stories in sports analytics' https://t.co/VZZMaCkCTj Order it now! https://t.co/9pXgr7xQxr

[A Gentleman @glenjaminc]

Alright, by popular demand, I've expanded this stats panel to include every single team in the majors.

https://t.co/TxiKOb1nPh

RTs appreciated!

[A Gentleman @glenjaminc]

I know Jays suck right now, but I built this anyway:

https://t.co/mleGDWfGC6

It's a daily stats panel that uses Fangraphs, MLB Stats and Savant data to show a ton of interesting information. I'm constantly adding new things too.

I made this for the people, so RTs appreciated.

[Wharton Moneyball @WMoneyball]

Today's show is available in Podcast Form NOW!

Richard Thaler, Nobel Laureate and Professor at the University of Chicago, and Benjamin Robinson, Founder of Grinding the Mocks discuss the impact of cognitive bias, valuation frameworks and data strategies on NFL draft selections.

Listen HERE: 👇👇👇
https://t.co/jxhhYx6i4Q

[zostaff @zostaff]

10 repos that mass replace a $100,000/year football analytics department. all free. all open source.

https://t.co/f88gBwzDuG -> replaces Hawkeye and Second Spectrum YOLO tracks every player and ball from any broadcast. assigns teams by jersey color. calculates speed, distance, possession. from a TV feed. no sensors.

https://t.co/It40HRL56i -> replaces entire quant sports desk stacked ensemble: LightGBM + XGBoost + Neural Networks + Random Forest. scrapes FBRef automatically. ELO with dynamic K-factor. Poisson xG. MongoDB backend. the most complete open-source football prediction pipeline on GitHub.

https://t.co/HBy8KHg5Vq -> replaces paid prediction platforms ($30/mo) full GUI app. 7 ML algorithms. downloads data from football-data. co. uk. predicts upcoming fixtures. exports to Excel. one click.

https://t.co/fbX02JGfYL -> replaces manual feature engineering XGBoost with 354 hand-crafted features. works for any European league. data straight from football-data. co. uk. plug and predict.

https://t.co/N4NBKWJ8yr -> replaces value bet scanners ($50/mo) ELO + expected goals + offensive/defensive ratings. compares model probability vs Vegas lines. flags when you have edge.

https://t.co/FEGRoaWs0x -> replaces bookmaker calibration tools Gradient Boosting tuned to output probabilities that match real bookmaker odds. not just accuracy - calibrated confidence.

https://t.co/LFzoWs4dcD -> replaces StatsBomb xG subscription xG model from KU Leuven researchers. LogReg + XGBoost pipelines. supports Wyscout, StatsBomb, Opta data. academic grade.

https://t.co/ZPQMuCwcAZ -> replaces xG analytics dashboards xG on StatsBomb open data. SHAP explanations for every prediction. proper calibration. tested on FIFA World Cup 2022.

https://t.co/tKj2sBOVzc -> replaces basic prediction models Poisson distribution for goal simulation. the classical approach that still beats most ML models on draw prediction.

https://t.co/Kp046GL1KL -> replaces Premier League prediction services XGBoost + AdaBoost + SVM on EPL data. detailed EDA. confusion matrices. honest 56% accuracy - because football is hard.

like + bookmark you'll need this when you build your first football prediction bot

[Vladislav Shufinskiy @vshufinskiy]

nba_data updated to full regular season 2025/2026.
Link on repo: https://t.co/mjlepcxfyz
#NBA #Analytics

[hockey-statistics @HockeySkytte]

My NHL site is now live!
https://t.co/hcfgTr8Gfx

There are many features that you can't find anywhere and I'm quite proud of this project.

However, I could really use your help spread the word. Please share the link here on Twitter/X, but also on other platforms. It means a lot

[nhlscraper @nhlscraper]

Version 0.6.0 has now been pushed to CRAN and will be rolling out to all users soon. This is a heavily recommended update for all. Check out the full change-log here: https://t.co/xv1HoejEYJ

[rahul @withqwerty]

if you work with football data, or want to start: meet nutmeg.

it's a set of AI skills and an MCP server that makes your coding agent aware of the world of football analytics. 10 skills across data acquisition, wrangling, analysis, and charting with one simple entry-point /nutmeg and searchable docs for 16 providers built in.

look up opta qualifier codes. brainstorm viz ideas. gather and wrangle data. learn the concepts. it adapts to where you're at.

in beta! works with claude code, codex, cursor, and 40+ other agents. feedback welcome!

https://t.co/G4uSUK1wAO

[Travis Sawchik @Travis_Sawchik]

How to - and how to not challenge calls - and how players are stacking up early this season: https://t.co/FqVpVezFXM

[Mike Petriello @mike_petriello]

If you want to see a team's total ABS challenge rate in one place (batting+fielders) you can do that now, here
https://t.co/vLdyeUa9PG

But also ...

[Billy Fryer @BillyFryer42]

Have you ever wanted to work with baseball player tracking data? Join the 5th Annual SMT Data Challenge! We'll help guide you through the End-to-End Data Science process through our new for 2026 Tutorial Series - available in both R and Python!

https://t.co/7t2RpXJ5rn

[SportsDataverse @sportsdataverse]

🏀 hoopR v3.0.0 is out now!

The biggest release yet for R's men's basketball data package — NBA Stats API, ESPN & G-League, all in one place.

install.packages("hoopR")

https://t.co/Xw3BVwh1lH
h/t: @SaiemGilani, @akeaswaran
#rstats #nba #sportsdataverse

[Developing Baseball @developbaseball]

More Statcast MCP! 24 @MLB data tools for AI clients: pitch-level Statcast, season & team stats, expected stats (incl. batch for full lineups), exit velo, arsenals, sprint speed, standings, percentiles, OAA, BRef streaks. We wanted more team/player lookups so you can access more data!⚾📊

Here is the link:

https://t.co/CND2IErUhu

#MLB #Sabermetrics #Statcast #MCP #OpenSource #Python

[basketballstrategy @bballstrategy]

https://t.co/da8aoOsImA

Sloan Conference paper

Deep Reinforcement Learning for NBA Player Valuation: A Temporal Difference Approach with Shapley Attribution