SOCCER player prop projection model. One of the edge-models family.
Give it a player's recent game log and a betting line. It returns a calibrated probability that the player goes over, plus a quarter Kelly stake. Trained on 16.0M synthesized lines pulled from real SOCCER game logs.
Held out test split (3.33M rows that the model never trained on):
| accuracy | brier | log loss | baseline | lift |
|---|---|---|---|---|
| 94% | 0.052 | 0.198 | 0.249 | +20.6% |
Lift is how much lower the calibrated log loss is than a no-skill baseline (0.051 absolute, 20.6% relative). Biggest sample (16M rows). Shots, passes and tackles are pretty predictable from recent form, so the lift holds up across a huge test set.
git clone https://github.com/LeSingh1/edge-soccer
cd edge-soccer
node src/predict.js --stat "Shots" --line 1.5 --log 2,1,3,0,2
Output is the projection, the raw over probability, the calibrated probability, and a suggested stake.
- Weight the recent games up and fit a mean and standard deviation.
- Turn the line into a raw over probability with a normal model.
- Correct that probability with the trained isotonic calibrator in
models/calibration.json. The correction is clamped to +/-0.20 so a thin bucket cannot fake confidence. - Size the bet with quarter Kelly.
The calibrator is keyed by stat type, so "Shots" gets a different correction than other stats.
The scraping pipeline and the raw training rows live in the private app this came out of. This repo ships the trained model and the code to run it, which is the useful part.
MIT. Not financial advice. The house edge is real, bet responsibly.