In The Game
  • Home
  • Football
    • Overview

    • Matches
    • Leagues

    • Player Stats
    • Player Ratings
    • Player Game Logs
    • Game Finder
    • Player Comparison

    • Team Stats
    • Team Game Logs
    • Team Ratings

    • World Cup 2026
    • Finals History
    • Player Stats (WC)
    • Wall Chart
    • Past Tournaments

    • Definitions
  • AFL
    • Overview

    • Matches
    • Ladder
    • Simulator
    • Draft 2026
    • Trade Grades

    • Player Stats
    • Player Ratings
    • Player Game Logs
    • Game Finder
    • Play Finder
    • Player Comparison
    • Age Curves

    • Team Stats
    • Team Game Logs
    • Team Ratings

    • Definitions
  • Athletics
    • Overview

    • Meet Forecast
    • Medal Table

    • Athlete Ratings
    • Model Report Card

    • Commonwealth Games 2026
    • Every Event
    • Games Event Detail
    • Athlete
  • Tennis
    • Overview

    • Draw Simulator
    • Upcoming Forecast
    • Player Ratings
  • Blog
  • Politics
    • Overview

    • Victoria 2026
    • New South Wales 2027

    • What if: Victoria
    • What if: New South Wales

    • Pollsters
    • Parties
  • Awards
    • Overview

    • Oscars
    • Golden Globes
    • Emmys
    • Grammys
  • About
Skip to content

Football · The Panna Project

Football

The week in football: who mattered most, how the title races stand, and what we expect next. Ratings and forecasts from Panna, our open-source player model.

Leagues Premier League La Liga Bundesliga Serie A Ligue 1 Champions League Europa League Conference League All leagues →

Every football page

How Panna works

Traditional football stats tell you what a player did. Panna ratings try to answer a harder question: how much did it actually matter?

The core idea is plus-minus: when a player is on the pitch, does their team create more and concede less than expected? Raw plus-minus is noisy (your numbers look great if you play alongside Messi), so the model controls for the quality of every other player on the field. Think of it as isolating your contribution from everyone else’s.

For players without enough minutes to get a reliable plus-minus estimate, the model falls back on box-score stats like key passes, interceptions and progressive carries, which tend to predict plus-minus well. The final Panna rating blends both signals, leaning more on the box score for bit-part players and more on plus-minus for regulars.

The rating splits into offense and defense. Positive offense means you’re helping create goals. Positive defense means you’re preventing them. Add them together and you get the overall picture.

 

Pete Owen · Sydney · © 2026 · Source

How our models work | My Teams | Settings | Photo Credits | Privacy | Disclaimer