Update app.py

app.py

@@ -111,9 +111,6 @@ def vector_to_score(vec: np.ndarray) -> float:
 # -----------------------------
 def get_decay_factor(num_headlines: int, max_headlines: int = MAX_HEADLINES,
                      min_decay: float = 0.6, max_decay: float = 0.95) -> float:
-    """
-    Dynamic decay: more headlines → higher decay → score can approach extremes.
-    """
     ratio = min(num_headlines / max_headlines, 1.0)
     return min_decay + ratio * (max_decay - min_decay)
 
@@ -127,31 +124,48 @@ class StocksRequest(BaseModel):
 
 @cached(stock_cache)
 def analyze_single_stock(stock: str) -> float | str:
+    # Fetch headlines
     headlines = fetch_headlines(stock)
     headlines = [h for h in headlines if h and len(h.strip()) > 10]
 
     if not headlines or len(headlines) < 2:
         return "NO_DATA"
 
+    # Ensemble sentiment
     vectors = [headline_score_ensemble(h) for h in headlines]
     agg = aggregate_headlines_vectors(vectors)
     raw_score = vector_to_score(agg)
 
-    # Apply dynamic decay
+    # Apply decay-weighted hybrid
     decay = get_decay_factor(len(headlines))
-    adjusted_score = 0.5 + decay * (raw_score - 0.5)
-    return round(adjusted_score, 2)
+    hybrid_score = 0.7 * raw_score + 0.3 * (0.5 + decay * (raw_score - 0.5))
+
+    # Market momentum adjustment (5-day price change)
+    try:
+        ticker = yf.Ticker(stock)
+        hist = ticker.history(period="5d")
+        if len(hist) >= 2:
+            change = (hist["Close"].iloc[-1] - hist["Close"].iloc[0]) / hist["Close"].iloc[0]
+            momentum_correction = np.clip(change * 2, -0.2, 0.2)  # ±0.2 max
+            final_score = np.clip(hybrid_score + momentum_correction, 0, 1)
+        else:
+            final_score = hybrid_score
+    except Exception as e:
+        print(f"[Market momentum error] {e}")
+        final_score = hybrid_score
+
+    return round(final_score, 2)
 
 @app.get("/")
 def root():
-    return {"message": "Fin-senti API is running! Use POST /analyze"}
+    return {"message": "Fin-senti API is live! Use POST /analyze"}
 
 @app.post("/analyze")
 def analyze(req: StocksRequest):
     results = {}
     for stock in req.stocks:
         results[stock] = analyze_single_stock(stock)
-    return results
+    return {"confidence_scores": results}
 
 if __name__ == "__main__":
     import uvicorn