Implement Regime Reversion Strategy and remove regime_detection.py

- Introduced `RegimeReversionStrategy` for ML-based regime detection and mean reversion trading.
- Added feature engineering and model training logic within the new strategy.
- Removed the deprecated `regime_detection.py` file to streamline the codebase.
- Updated the strategy factory to include the new regime strategy configuration.

strategies/factory.py

@@ -36,6 +36,7 @@ def _build_registry() -> dict[str, StrategyConfig]:
     # Import here to avoid circular imports
     from strategies.examples import MaCrossStrategy, RsiStrategy
     from strategies.supertrend import MetaSupertrendStrategy
+    from strategies.regime_strategy import RegimeReversionStrategy
     
     return {
         "rsi": StrategyConfig(
@@ -76,6 +77,19 @@ def _build_registry() -> dict[str, StrategyConfig]:
                 'period3': 12, 'multiplier3': 1.0
             }
         ),
+        "regime": StrategyConfig(
+            strategy_class=RegimeReversionStrategy,
+            default_params={
+                'horizon': 96,
+                'z_window': 24,
+                'stop_loss': 0.06,
+                'take_profit': 0.05
+            },
+            grid_params={
+                'horizon': [72, 96, 120],
+                'stop_loss': [0.04, 0.06, 0.08]
+            }
+        )
     }