feat: add autonomous paper-trading and calibration pipeline

backtest/backtest.py

@@ -214,6 +214,32 @@ def main():
     print(f"  20-day:  {a20:.1f}%  (n={n20})")
     print()
 
+
+    # baselines — what would naive strategies have scored on the same set?
+    # this is the most important context for interpreting the model accuracy above
+    eval_df = df[df["correct_10d"].notna()].copy()
+    if len(eval_df) > 0:
+        # 1. always-positive baseline — predict every event as bullish
+        eval_df["always_pos_correct"] = eval_df["10d_return"].apply(lambda r: r > 0 if r is not None else None)
+        always_pos = eval_df["always_pos_correct"].mean() * 100
+
+        # 2. random baseline — flip a coin for each prediction (analytic expectation = 50%)
+        # we report the empirical positive rate of the underlying market over the test window
+        # since random would converge to that for a balanced dataset
+        market_up_rate = (eval_df["10d_return"] > 0).mean() * 100
+
+        # 3. always-negative baseline
+        always_neg = ((eval_df["10d_return"] < 0).sum() / len(eval_df)) * 100
+
+        print("BASELINES (10-day, same evaluation set)")
+        print(f"  Always-positive:  {always_pos:.1f}%  (this is the bar to beat in a bull market)")
+        print(f"  Always-negative:  {always_neg:.1f}%")
+        print(f"  Random (coin):    50.0%  (analytic)")
+        print(f"  Market up rate:   {market_up_rate:.1f}%  (% of events where stock rose 10d later)")
+        edge = a10 - always_pos
+        print(f"  MODEL EDGE vs always-positive: {edge:+.1f} percentage points")
+        print()
+
     # by magnitude
     print("BY MAGNITUDE (10-day accuracy)")
     for mag in sorted(df["magnitude"].dropna().unique()):