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>

scripts/utils/notifier.py

@@ -107,14 +107,6 @@ class LottoNotifier:
         message += f"📅 *Generiert:* {timestamp}\n"
         message += f"📊 *Anzahl Tipps:* {len(tips)}\n\n"
 
-        # Bester Tipp
-        message += "⭐ *BESTER TIPP:*\n"
-        numbers_str = ' - '.join([f"{n:02d}" for n in best_tip['numbers']])
-        message += f"🎯 Zahlen: `{numbers_str}`\n"
-        message += f"🌟 Superzahl: `{best_tip['superzahl']}`\n"
-        message += f"📈 Confidence: `{best_tip['confidence']:.4f}`\n"
-        message += f"🎨 Strategie: `{best_tip['strategy']}`\n\n"
-
         # Statistiken
         avg_conf = sum(t['confidence'] for t in tips) / len(tips)
         avg_qual = sum(t['quality'] for t in tips) / len(tips)
@@ -123,16 +115,23 @@ class LottoNotifier:
         message += f"🎯 Ø Confidence: `{avg_conf:.4f}`\n"
         message += f"💎 Ø Quality: `{avg_qual:.4f}`\n\n"
 
-        # Top 3 Tipps
-        message += "🏆 *TOP 3 TIPPS:*\n"
-        sorted_tips = sorted(tips, key=lambda t: t['confidence'], reverse=True)[:3]
+        # Top 5 Tipps mit Details
+        message += "🏆 *TOP 5 EMPFEHLUNGEN:*\n"
+        message += "━━━━━━━━━━━━━━━━━━━━━━━\n"
+
+        sorted_tips = sorted(tips, key=lambda t: t['confidence'], reverse=True)[:5]
 
         for i, tip in enumerate(sorted_tips, 1):
-            nums = ' - '.join([f"{n:02d}" for n in tip['numbers']])
-            message += f"{i}. `{nums}` + SZ `{tip['superzahl']}` "
-            message += f"({tip['confidence']:.3f})\n"
+            # Emoji basierend auf Rang
+            emoji = "🏆" if i == 1 else "🥈" if i == 2 else "🥉" if i == 3 else "⭐"
 
-        message += "\n🍀 *Viel Glück!*"
+            nums = '-'.join([f"{n:02d}" for n in tip['numbers']])
+            message += f"\n{emoji} *#{i}* Conf: `{tip['confidence']:.2%}`\n"
+            message += f"🔢 `{nums}` + SZ `{tip['superzahl']}`\n"
+            message += f"📈 {tip['strategy']} | Q: `{tip['quality']:.3f}`\n"
+
+        message += "\n💡 Alle 10 Tipps in der CSV-Datei!\n"
+        message += "🍀 *Viel Glück!*"
 
         return message