Model Insight Console
A master lens for what moves the saved NBA model artifacts: global feature pressure, calibration honesty, confidence behavior, ablation lift, and market benchmarking.
Elo diff is the largest global SHAP driver in the held-out GBM explanation.
Logistic currently has the strongest log-loss profile among saved model artifacts.
The market benchmark is still better on matched closing-line log loss, so edge claims stay gated.
Game-level SHAP detail requires data/processed/shap_game_level.parquet in this worktree.
Logistic accuracy
66.8%
1,214 walk-forward rows
Log loss
0.605
Lower is better for calibrated probability quality
Brier score
0.210
Squared probability error across held-out games
Calibration gap
3.8%
Weighted mean bin gap between expected and observed
3D feature influence terrain
This surface combines report-backed SHAP rank with the selected model's confidence-band reliability. It is a visualization of saved artifacts, not a neural-network loss surface.
Selected ridge
Elo diff
Rank 1 · 0.2357 mean abs SHAP
Team-strength prior is the biggest global anchor before recent-form signals enter.
Why this model leans
Global SHAP magnitude from the GBM report. Directional per-game SHAP is shown as unavailable when the Parquet detail is not present.
Calibration truth table
Predicted home-win probability compared with observed home wins by probability band.
Confidence buckets
Volume bars show where the model usually lives; the line shows hit rate inside each confidence band.
Feature group mass
globalDecision anatomy status
Per-game explanation drilldown is gated by artifact availability.
Add data/processed/shap_game_level.parquet to unlock matchup-specific positive and negative contributors without guessing in the frontend.
Ablation ladder
Feature-stage runs stay separated from the dashboard; this view only reads their saved outputs.
Rolling base
Team rolling-form columns only.
62.7%
0.00 pts
Rest and travel
Rolling form plus rest, back-to-back, travel, and venue context.
63.3%
+0.66 pts
Matchup differentials
Rolling form plus team-vs-team differential features.
64.3%
+1.57 pts
No availability
Full feature set with availability columns removed.
63.7%
+0.99 pts
Full GBM
Current artifacted GBM with rolling, matchup, Elo, and availability features.
64.3%
+1.65 pts
Market reality check
Closing-line comparison keeps the dashboard honest about what the model has and has not beaten.
Matched odds
410
33.8% of saved predictions
Model log loss
0.598
Vegas 0.491 on matched games
Agreement
77.3%
Pick agreement with closing-line favorite
| Edge threshold | Games | Accuracy | ROI |
|---|---|---|---|
| 3% | 345 | 68.1% | -38.3% |
| 5% | 300 | 67.3% | -40.9% |
| 7% | 242 | 64.9% | -46.7% |
| 10% | 179 | 63.7% | -55.6% |
Artifact health
Missing artifacts are surfaced here instead of being guessed or recomputed in the browser.
Evaluation report
reports/evaluation_report.md
Source for global SHAP table and model narrative.
Updated Jun 30, 6:37 AM · 2,210 bytes
Summary metrics
reports/summary_metrics.csv
Artifact-backed model comparison metrics.
Updated Jun 30, 6:37 AM · 230 bytes
GBM backtest
reports/backtest_gbm.csv
Walk-forward rows used for calibration and confidence bins.
Updated Jun 30, 6:34 AM · 97,329 bytes
Ablation manifest
reports/ablations/latest/manifest.json
Feature-stage experiment provenance.
Updated May 7, 7:45 PM · 1,818 bytes
Market comparison
reports/market_comparison.json
Model-versus-closing-line benchmark.
Updated Jun 30, 6:37 AM · 1,502 bytes
Global SHAP parquet
data/processed/shap_global.parquet
Optional full global SHAP artifact; markdown fallback is used when absent.
Updated Jun 30, 6:37 AM · 4,256 bytes
Game-level SHAP parquet
data/processed/shap_game_level.parquet
Required for per-game directional explanations.
Updated Jun 30, 6:37 AM · 55,265 bytes
The dashboard reads prepared reports and backtests; it does not train models or invent predictions.
Global SHAP shows magnitude. Directional per-game reasons require the Parquet explanation artifact.
All headline model quality numbers come from walk-forward rows and saved comparison artifacts.