← All work09 / 11
Ten
Valorant Match PredictorForecasting esports matches with 180+ features.
Chapter concepts
- 1Role: Solo build.
- 2Status: Open source.
- 3Stack: Python, scikit-learn, XGBoost, LightGBM, Neural nets.
- 4Key figure: 180+ engineered features.
An ensemble ML system that predicts professional Valorant match outcomes from temporal form, team chemistry and economy.
The idea
Esports markets misprice matches constantly. If you can model a match better than the crowd, you have an edge. This is my second pass at doing exactly that for professional Valorant.
Exhibit 10-2
Data pipeline
- 1.Collect (augment.gg exports)→
- 2.Convert to CSV→
- 3.Build team-perspective rows→
- 4.Engineer 180+ features→
- 5.Train + cross-validate→
- 6.Predict with confidence
180+ engineered features
- 1Temporal weighting: recent form counts more
- 2Opponent-adjusted: strength of schedule
- 3Team chemistry: player synergy metrics
- 4Map-specific meta: per-map performance
- 5Clutch analytics: high-pressure rounds
- 6Economic efficiency: spend → impact
The model
No single model wins, so I blend several. A voting ensemble of Random Forest, XGBoost and LightGBM captures the tabular signal; a regularized neural network catches what they miss. The final prediction is a 70/30 blend of ensemble and network.
Exhibit 10-5
Key figures
70/30
ensemble · NN blend
3
boosted models voting
180+
features
At a glance
LanguagePython 3.8+
ModelsRF · XGBoost · LightGBM · NN
Dataaugment.gg match exports
InterfaceJupyter notebooks