diff --git a/model.py b/model.py
index 91a6f88..b090e6d 100644
--- a/model.py
+++ b/model.py
@@ -163,6 +163,9 @@ def calculate_adaptive_volatility(
     """
     Calculate volatility with adaptive window sizes based on market conditions.
     Returns a single volatility value for the most recent period.
+
+    Incorporates long-term volatility as a stability baseline and additional
+    reference point for regime detection.
     """
     df = df.copy()
     df["Log_Return"] = np.log(df["Close"]).diff()
@@ -190,10 +193,17 @@ def calculate_adaptive_volatility(
 
         # Calculate regime indicators for recent period
         medium_vol_mean = medium_vol.rolling(min(90, len(recent_df))).mean()
+        long_vol_mean = long_vol.rolling(min(180, len(recent_df))).mean()
+
         if medium_vol_mean.iloc[-1] == 0:
             vol_regime = pd.Series([1.0] * len(recent_df))
         else:
-            vol_regime = short_vol / medium_vol_mean
+            # Compare short-term to both medium and long-term volatility
+            medium_regime = short_vol / medium_vol_mean
+            long_regime = short_vol / long_vol_mean
+
+            # Use the more conservative (higher) regime indicator
+            vol_regime = pd.concat([medium_regime, long_regime], axis=1).max(axis=1)
 
         vol_regime = vol_regime.clip(vol_clip_min, vol_clip_max)
 
@@ -219,24 +229,26 @@ def calculate_adaptive_volatility(
         ]:
             return df["Log_Return"].std()
 
-        # Calculate regime-based weights
+        # Calculate regime-based weights, now incorporating long-term volatility
         high_vol_weight = (latest_regime - vol_clip_min) / (vol_clip_max - vol_clip_min)
-        base_weights = np.array([0.2, 0.5, 0.3])
-        stress_weights = np.array([0.4, 0.4, 0.2])
+        base_weights = np.array([0.2, 0.5, 0.3])  # Short, medium, long weights
+        stress_weights = np.array(
+            [0.4, 0.4, 0.2]
+        )  # More weight on short-term during stress
 
         # Interpolate between base and stress weights
         weights = (
             base_weights * (1 - high_vol_weight) + stress_weights * high_vol_weight
         )
 
-        # Calculate final volatility
+        # Calculate final volatility using all three timeframes
         final_vol = (
             final_short * weights[0]
             + final_medium * weights[1]
             + final_long * weights[2]
         )
 
-        # Add uncertainty adjustment
+        # Add uncertainty adjustment based on regime changes
         regime_change = abs(vol_regime.diff()).fillna(0)
         regime_change_mean = regime_change.rolling(5, min_periods=1).mean().iloc[-1]
         if regime_change_mean == 0: