mhaythornthwaite/Football_Prediction_Project
This project pulls past game data from api-football, and uses this to predict the outcome of future premier league matches with the use of classical machine learning techniques.
Constructs rolling 10-game performance metrics across 14 engineered features (goal difference, shot accuracy, possession, etc.) to capture relative team form, then trains scikit-learn classifiers (Random Forest, KNN, SVM) optimized via grid search and 5-fold cross-validation. The pipeline automatically refreshes from api-football's daily API calls, enabling continuous model retraining on recent fixtures while maintaining a nested dictionary structure organized by team and match ID for scalable data management.
285 stars.
Stars
285
Forks
87
Language
Python
License
MIT
Category
Last pushed
Mar 25, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mhaythornthwaite/Football_Prediction_Project"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
nickpadd/EuropeanFootballLeaguePredictor
A machine learning/statistical model to derive prediction probabilities for football matches of...
knaggita/Football-Dataset-Analysis
Football Dataset Analysis group project
octosport/octopy
Python implementation of various soccer/football analytics methods such as Poisson goals...
mcekovic/tennis-crystal-ball
Ultimate Tennis Statistics and Tennis Crystal Ball - Tennis Big Data Analysis and Prediction
MauroAndretta/AIFootballPredictions
AIFootballPredictions is an ML-based system to predict if a football match will have over 2.5...