Salil

⚽Wannabe Football Analyst

[Salil @salilftbl]

Would be interesting to see how he turns up the form after such a disappointing opener against DR Congo…

[Troll Football @TrollFootball]

Ronaldo watching Messi light up the World Cup from Portugal camp

[Salil @salilftbl]

@UTDIMole Al nassr ez

[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

[efStats @ef_Stats]

A football match contains ~1,600 on-ball actions. Traditional metrics (goals, assists, xG) evaluate fewer than 1% of them.

VAEP is the metric that values the other 99%. That's where hidden talent tends to surface. 🧵

[Salil @salilftbl]

Fr

[Justleavemealone @Novvigodly]

How it feels watching real Madrid games 😭

[rahul @withqwerty]

so this is where all the football data comes from

[Salil @salilftbl]

You know it’s summer when Virat Kohli returns in red and starts bashing bowlers all around the park.
Just pure class!

[Salil @salilftbl]

Just starting my journey into sports analytics — learning, experimenting, and figuring things out along the way.

Let’s see where this path takes me.

[Liam Henshaw @HenshawAnalysis]

5 years ago I was sharing these visuals online.

I made them in Canva and Tableau. I couldn't code. I'd never even created a full visual in Tableau alone - everything got finished off in Canva.

Looking at them now? There are things I'd never do today.

Radar charts with no context.
No sample sizes.
No upper or lower bounds.
Raw values instead of percentiles.

Plenty of mistakes.

But I was experimenting. Trying different formats. Using whatever data I could get my hands on. Learning by doing.

These visuals got me freelance work with a football agent.

That doesn't happen if I wait until the work is perfect.

Your early work doesn't need to be great. It needs to exist.

You need to take more shots.

You need to put yourself out there, get feedback, and improve.

Every visual I shared taught me something. And every post grew my network a little more.

The version of me that made these would be amazed at what came from just starting.

Start sharing. You'll look back and cringe too. That's the point.

What was the first thing you ever created in football?
I bet it was rough too.

[Salil @salilftbl]

Just published my first Medium article on football analysis ⚽📊

Took a deep dive into tactics, pressing structures, and how elite managers learns from each other. Would love your thoughts and feedback! 🙌
#FootballAnalytics #Tactics

https://t.co/xGOzVGKw0d

[Salil @salilftbl]

@Novvigodly Thanks!

[FootballEconomist @FootballEcon_]

Bruno Fernandes is having his most creative Premier League season yet, by being less attack-minded.

No longer so aggressive in forcing the ball forward, he is showing patience and maintaining possession under pressure, allowing attacks to form before executing his killer pass.

[Pranav @pranav_m28]

🔴Introducing Tempo Control Profiles

We often talk about tempo when talking about football. We talk about players who SET the tempo, players who CONTROL it or players who RAISE it.

So I decided to quantify it, visualise the actions and develop a classification system using data.

It divides the players into three main categories:
1. Tempo Catalyst - players who speed up the tempo
2. Tempo Conductor - players who maintain the tempo and have a right balance of slowing it down as well as increasing it
3. Tempo Settler - players who recycle more often, like to inject less

The framework has two main aspects: Injections and Resets. In simple terms, I look at the time gap between actions, compare the action to the recent rhythm of the sequence, and then judge whether it speeds the move up or slows it down. From there, I add territorial context as well, so quicker actions that also move the ball into more dangerous zones carry more value than quick actions with little tactical impact.

Here is Bruno's Tempo Control Profile. He falls under the Tempo Catalyst profile. Not surprising given how good he is at releasing quick incisive passes. Decent number of tempo increasing carries as well.

You can request for similar maps, specific lists and even drop suggestions and methods of improvement. I will share more results and try to improve this over the coming days.

[Football Analysis Hub @FtblAnalysisHub]

⚽️ HOW OFF THE BALL MOVEMENT BREAKS MAN TO MAN MARKING

✍️ Written by @FathalliMo

📲 Click to Read https://t.co/8mVsLTtYvY

[Justleavemealone @Novvigodly]

K. Mbappe 25/26 LaLiga+UCL review
Great player, highest xg chain
3rd highest xt in team (12,78)
Also great finishing
He have chances for ballon dor ? 🤔
#ucl #laliga #mbappe #data #python #football #visuals

[The Athletic | Football @TheAthleticFC]

Federico Valverde... that is sensational.

He seals his hat-trick with a delightful goal, touching it over Marc Guehi before smashing past Gianluigi Donnarumma.

Real Madrid lead Pep Guardiola's Manchester City 3-0.

[Salil @salilftbl]

What a player! What a match! Beautiful.

[Madrid Zone @theMadridZone]

FIRST HALF HATTRICK VS MANCHESTER CITY.

FEDE VALVERDE IS HIM. WOW!

[Salil @salilftbl]

R16 vs Man City
Éder Militão ❌
Dani Ceballos ❌
Jude Bellingham ❌
Kylian Mbappé ⚠️ (doubtful)
This isn’t just a match. It’s a test of character for Real Madrid.
#RealMadrid #ChampionsLeague2026

[Salil @salilftbl]

They debated his strike rate. He delivered victories for the country.
That’s the GOAT 🐐 for you 🫳🏻🎤

[Salil @salilftbl]

It’s great to finally have football back live in India ⚽️🇮🇳
#IndianSuperLeague #IndianFootball