LoL 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 0.2M synthesized lines pulled from real LoL game logs.
Held out test split (0.07M rows that the model never trained on):
| accuracy | brier | log loss | baseline | lift |
|---|---|---|---|---|
| 82.9% | 0.123 | 0.391 | 0.393 | +0.6% |
Lift is how much lower the calibrated log loss is than a no-skill baseline (0.002 absolute, 0.6% relative). League of Legends. Basically no edge (0.6% lift) and the sample is thin at 198k. I keep it for completeness but I would not bet it. Esports lines are sharp.
git clone https://github.com/LeSingh1/edge-lol
cd edge-lol
node src/predict.js --stat "Kills" --line 3.5 --log 4,2,5,3,6
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 "Kills" 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.