Update app/models.py

app/models.py

@@ -1,35 +1,82 @@
 from typing import Dict, Tuple
+import numpy as np
 import pandas as pd
 from xgboost import XGBRegressor
 from .features import FEATURE_COLUMNS
 
+
+def _zscore(series: pd.Series) -> pd.Series:
+    std = float(series.std(ddof=0))
+    if std < 1e-12:
+        return pd.Series(np.zeros(len(series)), index=series.index)
+    return (series - float(series.mean())) / std
+
+
 def train_model(feature_df: pd.DataFrame) -> Tuple[XGBRegressor, pd.DataFrame]:
     X = feature_df[FEATURE_COLUMNS]
     y = feature_df["target_return_5d"]
+
     model = XGBRegressor(
-        n_estimators=120,
+        n_estimators=200,
         max_depth=4,
-        learning_rate=0.05,
+        learning_rate=0.04,
         subsample=0.9,
         colsample_bytree=0.9,
         objective="reg:squarederror",
         random_state=42,
         n_jobs=2,
+        reg_alpha=0.1,
+        reg_lambda=1.0,
         enable_categorical=False,
     )
     model.fit(X, y)
     return model, feature_df
 
-def latest_predictions(model: XGBRegressor, feature_df: pd.DataFrame) -> pd.DataFrame:
-    latest = feature_df.sort_values("date").groupby("ticker", as_index=False).tail(1).reset_index(drop=True)
-    latest["predicted_return"] = model.predict(latest[FEATURE_COLUMNS])
+
+def build_alpha_signals(model: XGBRegressor, feature_df: pd.DataFrame) -> pd.DataFrame:
+    latest = (
+        feature_df.sort_values("date")
+        .groupby("ticker", as_index=False)
+        .tail(1)
+        .reset_index(drop=True)
+        .copy()
+    )
+
+    latest["model_pred"] = model.predict(latest[FEATURE_COLUMNS])
+
+    latest["pred_z"] = _zscore(latest["model_pred"])
+    latest["mom_z"] = _zscore(latest["ret_20d"].fillna(0.0))
+    latest["trend_z"] = _zscore(latest["ma_ratio_10_50"].fillna(0.0))
+    latest["low_vol_z"] = _zscore(-latest["vol_20d"].fillna(0.0))
+    latest["volume_z2"] = _zscore(latest["volume_z"].fillna(0.0))
+
+    latest["alpha_score"] = (
+        0.55 * latest["pred_z"]
+        + 0.20 * latest["mom_z"]
+        + 0.15 * latest["trend_z"]
+        + 0.05 * latest["low_vol_z"]
+        + 0.05 * latest["volume_z2"]
+    )
+
+    latest["alpha_score"] = latest["alpha_score"].clip(-3.0, 3.0)
+
+    base_daily = 0.0002
+    spread_daily = 0.0030
+    latest["expected_return"] = base_daily + spread_daily * latest["alpha_score"]
+
     return latest
 
+
 def top_feature_contributions(model: XGBRegressor, latest_df: pd.DataFrame, top_n: int = 5) -> Dict[str, list]:
     booster = model.get_booster()
     raw_gain = booster.get_score(importance_type="gain") or {}
-    gain_map = {name: float(raw_gain.get(f"f{i}", 0.0)) for i, name in enumerate(FEATURE_COLUMNS)}
+
+    gain_map = {}
+    for i, name in enumerate(FEATURE_COLUMNS):
+        gain_map[name] = float(raw_gain.get(f"f{i}", 0.0))
+
     ranked = sorted(gain_map.items(), key=lambda x: x[1], reverse=True)[:top_n]
+
     template = [{"feature": f, "contribution": v} for f, v in ranked]
     if not template:
         template = [
@@ -37,4 +84,5 @@ def top_feature_contributions(model: XGBRegressor, latest_df: pd.DataFrame, top_
             {"feature": "momentum_factor", "contribution": 0.0},
             {"feature": "market_return", "contribution": 0.0},
         ]
-    return {ticker: template for ticker in latest_df["ticker"].tolist()}
+
+    return {ticker: template for ticker in latest_df["ticker"].tolist()}