feat: report bootstrap confidence intervals

backtesting/engine.py

@@ -11,6 +11,7 @@ from datetime import datetime, timedelta
 
 from scoring.policy import SCORE_BRACKETS, SCORE_VERSION, score_in_bracket
 from ml.artifacts import validate_ml_artifact
+from backtesting.statistics import summarize_returns
 
 log = logging.getLogger(__name__)
 
@@ -419,6 +420,19 @@ def clear_backtest_cache():
         _BACKTEST_CACHE.clear()
 
 
+def _add_return_statistics(stats, period, returns):
+    """Add return summaries and a moving-block-bootstrap mean interval."""
+    summary = summarize_returns(returns, block_size=min(30, len(returns)), n_resamples=400)
+    stats[f"avg_{period}"] = summary["mean"]
+    stats[f"median_{period}"] = summary["median"]
+    stats[f"win_rate_{period}"] = summary["win_rate"]
+    stats[f"avg_{period}_ci_low"] = summary["mean_ci_low"]
+    stats[f"avg_{period}_ci_high"] = summary["mean_ci_high"]
+    stats[f"max_gain_{period}"] = round(max(returns), 2)
+    stats[f"max_loss_{period}"] = round(min(returns), 2)
+    stats[f"n_{period}"] = summary["n"]
+
+
 def run_backtest(ml_mode=False):
     """Return an isolated cached result keyed by all material input files."""
     signature = (
@@ -537,13 +551,7 @@ def _compute_backtest(ml_mode=False):
         for period in ["30d", "90d", "180d", "365d"]:
             returns = [d["forward_returns"][period] for d in days_in if period in d["forward_returns"]]
             if returns:
-                returns_sorted = sorted(returns)
-                stats[f"avg_{period}"] = round(sum(returns) / len(returns), 2)
-                stats[f"median_{period}"] = round(returns_sorted[len(returns_sorted) // 2], 2)
-                stats[f"win_rate_{period}"] = round(len([r for r in returns if r > 0]) / len(returns) * 100, 1)
-                stats[f"max_gain_{period}"] = round(max(returns), 2)
-                stats[f"max_loss_{period}"] = round(min(returns), 2)
-                stats[f"n_{period}"] = len(returns)
+                _add_return_statistics(stats, period, returns)
 
         # Average max drawdown within 90 days
         dd_list = []

tests/test_backtest_statistics.py

@@ -1,4 +1,4 @@
-from backtesting import statistics
+from backtesting import engine, statistics
 
 
 def test_moving_block_bootstrap_is_deterministic_and_handles_constant_series():
@@ -32,3 +32,14 @@ def test_summarize_returns_reports_observations_and_block_bootstrap_interval():
     assert summary["median"] == 2.5
     assert summary["win_rate"] == 50.0
     assert summary["mean_ci_low"] <= summary["mean"] <= summary["mean_ci_high"]
+
+
+def test_backtest_brackets_publish_bootstrap_confidence_intervals():
+    stats = {}
+
+    engine._add_return_statistics(stats, "90d", [10.0, -5.0, 20.0, -10.0])
+
+    assert stats["avg_90d"] == 3.75
+    assert stats["median_90d"] == 2.5
+    assert stats["win_rate_90d"] == 50.0
+    assert stats["avg_90d_ci_low"] <= stats["avg_90d"] <= stats["avg_90d_ci_high"]