Eight separate models. One for every CS2 map.
About this Model
MIRAGE is a collection of eight independent LightGBM models — one per active CS2 map. Each model is trained exclusively on historical results for its specific map, capturing map-specific team specializations that a single global model misses. Features include map Elo history, CT/T win rates with economy stratification, player lineup quality (CT/T per-player rolling win rates from demo data), and side-specific momentum. MIRAGE v6 introduces lineup-level features: per-player rolling CT/T win rates aggregated to team level, enabling detection of individual map specialists.
Top Feature Drivers
Per-map team Elo from match history (elo_before — no leakage)
Baseline quality gap (map-independent anchor)
Which team dominates CT rifle rounds on this map
Bomb-plant conversion gap — T-side aggression edge
Average CT win rate of each player's history on this map
Opponent-quality-weighted side win rates
CT eco vs T eco efficiency gap
CT wins on T full-buys — defensive specialist signal
Feature importances reflect normalized split gain across the training set. Values are approximate — the model uses all features simultaneously.
Per-Map AUC Breakdown
AUC measured on chronologically held-out test split per map.
How to Interpret
MIRAGE win probability for a specific map tells you how likely each team is to win that exact map based on all available historical signal for that map only. Use the per-map scores during veto analysis: a large MIRAGE edge (>10pp) on a map means it's a priority pick for the stronger team and a priority ban for the weaker one. Nuke currently has the strongest discriminative power (AUC 0.638); anubis is noisiest.
Live Performance
Selector Role
Sub-model — per-map win probabilities feed into TITAN and the veto advisor.
Version History
First per-map LightGBM; mean AUC 0.603
+CT/T side win rates from demo_rounds; mean AUC 0.608
+per-map regularization, exp-decay CT/T, auto-pruning; mean AUC 0.612
+economy buy-type stratification; nuke AUC 0.641 (best ever)
+player lineup CT/T win rates; ancient/overpass new bests; mean AUC 0.615