📊 Model Performance Comparison

Compare accuracy, PnL, and risk metrics per model; each row covers every version of the model

← Back to Dashboard
Model Predictions Accuracy Avg Error % Total PnL Win Rate Sharpe Max drawdown Always-up Persistence Buy & hold PnL vs best baseline
linear 93 versions, trained on data up to 2026-07-31 to 2026-11-01 ACTIVE 🏆 Best Return 92 50.0% 1.3% $16,042.21 28.3% 2.94 -7.74% 51.1% n=92 51.1% n=92 $14,694.14 ✗ Does not beat baseline -1.1 pts vs always-up, p=0.623, n=92

Baselines are scored on the same days as each model. Always-up predicts a rise every day; persistence repeats yesterday's direction. A model beats the baseline only when its accuracy is higher and the gap is statistically significant (one-sided binomial test, p < 0.05). Baselines are available for the daily timeframe only.

Cumulative PnL by Model