Backtesting
Score Your Model With the Brier Score
Compare a naive baseline, an Elo model and margin-free market odds on 2,660 Premier League matches with the Brier score, in Python.
Read the tutorial →How to test a football model honestly: out-of-sample data, proper scoring rules and the mistakes that make backtests look better than reality.
A backtest shows how a model would have done in the past — and it is easy to fool yourself. This section covers out-of-sample testing, scoring rules such as the Brier score and log loss, and the common mistakes that inflate results.
No backtest guarantees future results.
Compare a naive baseline, an Elo model and margin-free market odds on 2,660 Premier League matches with the Brier score, in Python.
Read the tutorial →Build a reliability table in pandas and test whether market and Elo home-win forecasts come true as often as they claim, on 2,660 matches.
Read the tutorial →