Add Deep Learning (LSTM) + Quick Wins automation features

Major improvements:
- Deep Learning integration with PyTorch LSTM (Bidirectional, 128→64 units)
- Hybrid predictor: 40% RandomForest + 60% Deep Learning
- LaunchAgent for automatic weekly tip generation (Tue/Fri 21:00)
- Health-Check system with auto-recovery and Telegram alerts
- Model caching and intelligent retraining logic
- Updated CSV data and generated tips
- Performance reports for recent draws

Technical details:
- PyTorch used instead of TensorFlow (Python 3.14 compatibility)
- Apple Silicon MPS acceleration support
- Sequence learning with 20-draw history
- Early stopping and learning rate scheduling

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>

data/ultimate_ml_models/deep_learning/lstm_config_49.json

@@ -0,0 +1,9 @@
+{
+  "trained_at": "2026-01-05T14:26:53.036260",
+  "num_samples": 4954,
+  "num_features": 20,
+  "final_loss": 0.3721399052489188,
+  "final_val_loss": 0.3729977588499746,
+  "best_val_loss": 0.37259673303173435,
+  "epochs_trained": 30
+}

data/ultimate_ml_models/learning_state.json

@@ -0,0 +1,61 @@
+{
+  "adjustments": {
+    "1": -0.019751246878125,
+    "2": -0.019751246878125,
+    "3": -0.004826246878125001,
+    "4": -0.019751246878125,
+    "5": -0.019751246878125,
+    "6": -0.019751246878125,
+    "7": 0.009875251246875,
+    "8": 0.009949876246875,
+    "9": -0.019751246878125,
+    "10": -0.004900871878125002,
+    "11": -0.004826246878125001,
+    "12": 0.00987599563125,
+    "13": -0.019751246878125,
+    "14": -0.019751246878125,
+    "15": -0.019751246878125,
+    "16": -0.004826246878125001,
+    "17": -0.019751246878125,
+    "18": -0.019751246878125,
+    "19": -0.019751246878125,
+    "20": -0.019751246878125,
+    "21": -0.019751246878125,
+    "22": -0.019751246878125,
+    "23": -0.0050490043687499995,
+    "24": -0.019751246878125,
+    "25": -0.004975123753125,
+    "26": -0.019751246878125,
+    "27": -0.004900871878125002,
+    "28": -0.004900871878125002,
+    "29": -0.019751246878125,
+    "30": -0.019751246878125,
+    "31": -0.019751246878125,
+    "32": 0.00972711875625,
+    "33": -0.0050490043687499995,
+    "34": -0.019751246878125,
+    "35": -0.019751246878125,
+    "36": -0.019751246878125,
+    "37": -0.004975123753125,
+    "38": -0.004900871878125002,
+    "39": -0.004975123753125,
+    "40": -0.0050490043687499995,
+    "41": -0.019751246878125,
+    "42": -0.0050490043687499995,
+    "43": -0.019751246878125,
+    "44": -0.019751246878125,
+    "45": -0.019751246878125,
+    "46": 0.010024128121874998,
+    "47": -0.019751246878125,
+    "48": -0.019751246878125,
+    "49": -0.019751246878125
+  },
+  "stats": {
+    "incorrect": 172,
+    "correct": 24,
+    "cycles": 4,
+    "last_update": "2026-01-05T11:56:39.904258"
+  },
+  "learning_rate": 0.1,
+  "last_saved": "2026-01-05T11:56:39.904307"
+}