fix: IC chart cumulative mean + forward return horizon matching + multi-horizon eval

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

run_example.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-"""End-to-end pipeline: HS300 universe -> momentum signal -> cross-sectional IC
+"""End-to-end pipeline: HS300 universe -> reversal signal -> cross-sectional IC
 -> multi-stock backtest (AlphaStrategy + RankEqualWeightBuilder) -> reports."""
 import logging
 
@@ -12,14 +12,24 @@ from data.downloader import download_batch
 from data.universe import SYMBOLS
 from eval.metrics import evaluate_cross_sectional
 from portfolio.builder import RankEqualWeightBuilder
-from signals.momentum import MomentumSignal
+from signals.reversal import ReversalSignal
 from strategies.alpha_strategy import AlphaStrategy
 
 logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
 logger = logging.getLogger(__name__)
 
 
-def main():
+def _forward_returns(data: dict[str, pd.DataFrame], horizon: int) -> pd.DataFrame:
+    """Build a date-indexed DataFrame of ``horizon``-day forward returns per stock."""
+    forward_returns: dict[str, pd.Series] = {}
+    for sym, df in data.items():
+        fwd = df["close"].pct_change(horizon).shift(-horizon)
+        fwd.index = pd.to_datetime(df["date"])
+        forward_returns[sym] = fwd
+    return pd.DataFrame(forward_returns)
+
+
+def main(forward_horizon: int = 5):
     symbols = SYMBOLS[:30]
     start, end = "2023-01-01", "2024-12-31"
     initial_cash = 1_000_000
@@ -29,24 +39,25 @@ def main():
     data = {s: df for s, df in data.items() if df is not None and not df.empty}
     logger.info(f"Downloaded {len(data)}/{len(symbols)} symbols")
 
-    # 3. Compute the momentum signal per stock.
-    signal = MomentumSignal(lookback=5)
+    # 3. Compute the reversal signal per stock.
+    signal = ReversalSignal(lookback=5)
     signal_series: dict[str, pd.Series] = {}
-    forward_returns: dict[str, pd.Series] = {}
     for sym, df in data.items():
-        idx = pd.to_datetime(df["date"])
         sig = signal.compute(df)
-        sig.index = idx
+        sig.index = pd.to_datetime(df["date"])
         signal_series[sym] = sig
-        fwd = df["close"].pct_change().shift(-1)  # next-day return
-        fwd.index = idx
-        forward_returns[sym] = fwd
 
-    # 4. Cross-sectional IC evaluation.
+    # 4. Cross-sectional IC at the matching forward horizon.
     signals_df = pd.DataFrame(signal_series)
-    returns_df = pd.DataFrame(forward_returns)
+    returns_df = _forward_returns(data, forward_horizon)
     signal_eval = evaluate_cross_sectional(signals_df, returns_df)
 
+    # 4b. Multi-horizon IC to show which horizon the signal works at.
+    horizon_evals = {
+        h: evaluate_cross_sectional(signals_df, _forward_returns(data, h))
+        for h in (1, 5, 20)
+    }
+
     # 5. Attach the signal column to each DataFrame and build feeds.
     config = BacktestConfig(
         symbols=list(data.keys()),
@@ -79,6 +90,14 @@ def main():
           f"{signal_eval['rank_ic_std']:.4f} / {signal_eval['rank_ir']:.4f}")
     print(f"Hit rate:                 {signal_eval['hit_rate']:.2%}")
     print(f"Periods:                  {signal_eval['n_periods']}")
+
+    print("\nMULTI-HORIZON IC")
+    print("=" * 50)
+    print(f"{'Horizon':>8}  {'Rank IC':>9}  {'Rank IR':>9}  {'Hit rate':>9}  {'Periods':>8}")
+    for h, ev in horizon_evals.items():
+        print(f"{f'{h}d':>8}  {ev['rank_ic_mean']:>9.4f}  {ev['rank_ir']:>9.4f}  "
+              f"{ev['hit_rate']:>8.2%}  {ev['n_periods']:>8}")
+
     print(f"\nReports written to: {artifacts}")