Altora Analysis
CS2 · LoL · Dota 2 — calibrated model analysis, not tips. Tracked in the open.
Today · 2026-09-04
Model win probability for today's matches — not tips. These settle into the record below.
Model validation · 13,586 out-of-sample matches · to 2026-07-30
These are matches the model never trained on. It picks the winner 62% of the time and its probabilities are calibrated. On esports the market is sharper than the model — it sees team news (rotations, injuries, rested players) that a results-based model can't — so we show that gap openly rather than hide it.
Reliability — model probability predicted vs what actually happened
The bars line up on every band — the model is honestly calibrated. It isn't as sharp as the market on esports, and we say so. Analysis in the open, not tips.
Since 21 July 2026, Dota 2 matches are priced by a dedicated Dota model (rating built from 114,000+ professional games with margin-of-victory weighting). CS2 and League of Legends continue on the shared model. The validation numbers above pre-date this change; the Dota model's own record accrues in the live table below and will be reported separately once the sample is meaningful.
The live record · every pick since going public
Esports runs year-round (CS2, LoL, Dota 2). Nothing deleted — wins and losses, every one. The validation above is the model's accuracy over thousands of past matches.
| Date | Model pick | Prob | Result |
|---|---|---|---|
| 5 voided match(es) shown greyed below — kept on the record, excluded from the accuracy figures (no result to score). | |||
| 2026-09-03 | dplus kia v bnk fearx | 74% | W |
| 2026-09-02 | hanwha life esports v t1 | 67% | W |
| 2026-09-02 | heroic v 3dmax | 56% | W |
| 2026-09-02 | mibr v eternal fire | 72% | L |
| 2026-09-02 | magic v k27 | 64% | W |
| 2026-09-02 | big v nemiga | 67% | L |
| 2026-09-02 | hotu v pain | 56% | W |
| 2026-09-02 | b8 v color | 71% | W |
| 2026-09-02 | gamerlegion v nuclear tigeres | 53% | VOID |
| 2026-08-31 | spirit v furia | 69% | W |
| 2026-08-31 | g2 v aurora gaming | 52% | W |
| 2026-08-31 | team falcons v mouz | 58% | L |
| 2026-08-30 | dplus kia v kt rolster | 75% | L |
| 2026-08-30 | natus vincere v g2 | 55% | L |
| 2026-08-30 | aurora gaming v m80 | 66% | W |
| 2026-08-30 | team vitality v shifters | 80% | W |
| 2026-08-30 | movistar koi v team heretics | 78% | W |
| 2026-08-30 | fnatic v giantx | 52% | L |
| 2026-08-30 | lyon v team liquid | 52% | W |
| 2026-08-29 | vitality v 9z | 77% | W |
| 2026-08-29 | mouz v inner circle esports | 75% | W |
| 2026-08-29 | fut esports v lynn vision | 73% | W |
| 2026-08-29 | team falcons v legacy | 60% | W |
| 2026-08-29 | natus vincere v giantx | 53% | W |
| 2026-08-28 | natus vincere v pain | 77% | W |
| 2026-08-28 | team heretics v shifters | 56% | L |
| 2026-08-28 | furia v m80 | 71% | W |
| 2026-08-28 | team vitality v fnatic | 57% | W |
| 2026-08-27 | mouz v 9z | 62% | W |
| 2026-08-27 | vitality v inner circle esports | 90% | L |
⬇ Download the full record (CSV — opens in Excel / Sheets) · showing the most recent 30 of 224
Model updated 22 July 2026: published probabilities now blend the Elo rating with the market opening price through a gradient-boosted calibration layer, validated out-of-sample before switching. The record below spans both model versions.