diff --git a/.gitignore b/.gitignore
index 4fa77e0..b084b3e 100644
--- a/.gitignore
+++ b/.gitignore
@@ -53,3 +53,10 @@ logs/*.log
 
 # Performance reports (optional)
 # ai_performance_report_*.json
+
+# Backups und generierte Outputs
+data/backups/
+data/*.backup*
+data/generated_tips/weekly_lotto_tips_*.csv
+data/performance_reports/
+data/data/
diff --git a/data/AlleLottozahlen.csv b/data/AlleLottozahlen.csv
index 28d0178..dc218ad 100644
--- a/data/AlleLottozahlen.csv
+++ b/data/AlleLottozahlen.csv
@@ -3095,3 +3095,33 @@ datum;Z1;Z2;Z3;Z4;Z5;Z6;SZ
 2026-01-24;1;7;28;32;47;49;1
 2026-01-28;9;11;25;35;37;44;3
 2026-01-31;8;19;30;37;38;49;3
+2026-02-04;9;11;16;22;27;37;0
+2026-02-07;7;11;20;25;28;49;7
+2026-02-11;8;9;18;20;37;40;3
+2026-02-14;3;9;19;20;40;43;7
+2026-02-18;10;15;19;20;29;48;8
+2026-02-21;2;8;9;29;39;44;6
+2026-02-25;9;13;25;30;37;46;8
+2026-02-28;1;6;19;33;44;45;8
+2026-03-04;1;15;17;24;37;40;3
+2026-03-07;5;16;20;38;39;41;4
+2026-03-11;17;21;26;32;35;37;0
+2026-03-14;19;20;28;32;44;45;0
+2026-03-18;10;13;20;35;43;49;0
+2026-03-21;2;7;19;24;29;43;2
+2026-03-25;7;12;29;30;46;49;5
+2026-03-28;5;20;24;33;34;42;1
+2026-04-01;8;10;11;14;22;48;1
+2026-04-04;6;15;18;23;28;48;2
+2026-04-08;2;5;14;16;23;36;8
+2026-04-11;17;23;32;33;34;46;0
+2026-04-15;3;17;25;28;40;42;0
+2026-04-18;18;28;34;37;44;48;4
+2026-04-22;15;26;27;35;42;47;5
+2026-04-25;6;12;15;20;35;49;9
+2026-04-29;1;15;25;37;43;47;4
+2026-05-02;1;5;9;20;21;32;5
+2026-05-06;10;13;19;38;40;48;2
+2026-05-09;2;3;12;36;39;43;8
+2026-05-13;13;15;20;26;31;43;7
+2026-05-16;7;11;20;23;27;30;9
diff --git a/data/generated_tips/generation_history.json b/data/generated_tips/generation_history.json
index a87627b..1055edf 100644
--- a/data/generated_tips/generation_history.json
+++ b/data/generated_tips/generation_history.json
@@ -174,6 +174,216 @@
       "file": "weekly_lotto_tips_20260203_210148.csv",
       "avg_confidence": 0.43053407858302783,
       "avg_quality": 0.6127569878171568
+    },
+    {
+      "timestamp": "2026-02-06T21:24:33.178900",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260206_212433.csv",
+      "avg_confidence": 0.39179800156619443,
+      "avg_quality": 0.5831545873566034
+    },
+    {
+      "timestamp": "2026-02-10T21:00:22.150517",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260210_210022.csv",
+      "avg_confidence": 0.43625158283574716,
+      "avg_quality": 0.6169535402692883
+    },
+    {
+      "timestamp": "2026-02-13T21:00:21.382316",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260213_210021.csv",
+      "avg_confidence": 0.43088261472508316,
+      "avg_quality": 0.6109923873184334
+    },
+    {
+      "timestamp": "2026-02-17T21:00:26.043929",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260217_210026.csv",
+      "avg_confidence": 0.42905107467438075,
+      "avg_quality": 0.6160959707954421
+    },
+    {
+      "timestamp": "2026-02-20T21:00:26.545065",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260220_210026.csv",
+      "avg_confidence": 0.43055460012609004,
+      "avg_quality": 0.6159742993010366
+    },
+    {
+      "timestamp": "2026-02-24T21:00:15.456660",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260224_210015.csv",
+      "avg_confidence": 0.4389957217440533,
+      "avg_quality": 0.6166952308149034
+    },
+    {
+      "timestamp": "2026-02-27T21:00:26.214280",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260227_210026.csv",
+      "avg_confidence": 0.41380590175304316,
+      "avg_quality": 0.6007363719044858
+    },
+    {
+      "timestamp": "2026-03-03T21:00:30.382128",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260303_210030.csv",
+      "avg_confidence": 0.6131651661650304,
+      "avg_quality": 0.7146464746308903
+    },
+    {
+      "timestamp": "2026-03-06T21:00:24.428265",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260306_210024.csv",
+      "avg_confidence": 0.39974949595009224,
+      "avg_quality": 0.5881493624603976
+    },
+    {
+      "timestamp": "2026-03-10T21:05:18.962145",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260310_210518.csv",
+      "avg_confidence": 0.43571892829509284,
+      "avg_quality": 0.619982489791712
+    },
+    {
+      "timestamp": "2026-03-13T21:01:53.225581",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260313_210153.csv",
+      "avg_confidence": 0.4111754357415879,
+      "avg_quality": 0.6009998715375982
+    },
+    {
+      "timestamp": "2026-03-17T21:00:32.536342",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260317_210032.csv",
+      "avg_confidence": 0.4207776853663847,
+      "avg_quality": 0.6117993361098875
+    },
+    {
+      "timestamp": "2026-03-20T21:16:55.124861",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260320_211655.csv",
+      "avg_confidence": 0.4029942661902326,
+      "avg_quality": 0.5898327020762006
+    },
+    {
+      "timestamp": "2026-03-24T21:01:28.095284",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260324_210128.csv",
+      "avg_confidence": 0.4245373981596304,
+      "avg_quality": 0.6094510518762004
+    },
+    {
+      "timestamp": "2026-03-27T21:00:28.070123",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260327_210028.csv",
+      "avg_confidence": 0.42596489621339506,
+      "avg_quality": 0.614192879963136
+    },
+    {
+      "timestamp": "2026-03-31T21:00:20.282697",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260331_210020.csv",
+      "avg_confidence": 0.4311573904241078,
+      "avg_quality": 0.6143222769705906
+    },
+    {
+      "timestamp": "2026-04-03T21:46:54.466732",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260403_214654.csv",
+      "avg_confidence": 0.40367778119537806,
+      "avg_quality": 0.5978802314336015
+    },
+    {
+      "timestamp": "2026-04-07T21:00:23.043609",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260407_210023.csv",
+      "avg_confidence": 0.42841389944709796,
+      "avg_quality": 0.613680679288901
+    },
+    {
+      "timestamp": "2026-04-10T21:00:21.478887",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260410_210021.csv",
+      "avg_confidence": 0.4201527267401346,
+      "avg_quality": 0.6037242036565935
+    },
+    {
+      "timestamp": "2026-04-14T21:00:20.493117",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260414_210020.csv",
+      "avg_confidence": 0.4201339358438558,
+      "avg_quality": 0.6070767820478455
+    },
+    {
+      "timestamp": "2026-04-17T21:00:21.627397",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260417_210021.csv",
+      "avg_confidence": 0.40653731661730175,
+      "avg_quality": 0.5959122317720231
+    },
+    {
+      "timestamp": "2026-04-21T21:00:21.291830",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260421_210021.csv",
+      "avg_confidence": 0.4281003982558874,
+      "avg_quality": 0.6180774622190407
+    },
+    {
+      "timestamp": "2026-04-24T21:00:21.813713",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260424_210021.csv",
+      "avg_confidence": 0.40368288784557055,
+      "avg_quality": 0.590237489018969
+    },
+    {
+      "timestamp": "2026-04-28T21:16:39.462043",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260428_211639.csv",
+      "avg_confidence": 0.38479137617697334,
+      "avg_quality": 0.5730525563530181
+    },
+    {
+      "timestamp": "2026-05-01T21:13:28.620453",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260501_211328.csv",
+      "avg_confidence": 0.41358937770573123,
+      "avg_quality": 0.5981172891531314
+    },
+    {
+      "timestamp": "2026-05-05T21:00:21.883272",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260505_210021.csv",
+      "avg_confidence": 0.39151792949512265,
+      "avg_quality": 0.5835184310224573
+    },
+    {
+      "timestamp": "2026-05-08T21:00:27.261943",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260508_210027.csv",
+      "avg_confidence": 0.39430951299665706,
+      "avg_quality": 0.5770382849355139
+    },
+    {
+      "timestamp": "2026-05-12T21:00:21.984425",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260512_210021.csv",
+      "avg_confidence": 0.4339787527079359,
+      "avg_quality": 0.6033231576498798
+    },
+    {
+      "timestamp": "2026-05-15T21:00:21.046302",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260515_210021.csv",
+      "avg_confidence": 0.41244722617171564,
+      "avg_quality": 0.5996401924263831
+    },
+    {
+      "timestamp": "2026-05-19T13:32:39.647439",
+      "num_tips": 10,
+      "file": "weekly_lotto_tips_20260519_133239.csv",
+      "avg_confidence": 0.4215215125819441,
+      "avg_quality": 0.5999271737766253
     }
   ]
 }
\ No newline at end of file
diff --git a/data/learning_log.json b/data/learning_log.json
index 6205cee..0436d53 100644
--- a/data/learning_log.json
+++ b/data/learning_log.json
@@ -186,6 +186,408 @@
         "main": 0.9,
         "sz_rate": 0.1
       }
+    },
+    {
+      "timestamp": "2026-02-07T20:00:50.951491",
+      "draw_date": "2026-02-04",
+      "evaluation": {
+        "main": 2,
+        "sz": false,
+        "tip": 3
+      },
+      "avg_matches": {
+        "main": 0.7,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-02-11T20:01:02.668200",
+      "draw_date": "2026-02-07",
+      "evaluation": {
+        "main": 2,
+        "sz": true,
+        "tip": 7
+      },
+      "avg_matches": {
+        "main": 0.6,
+        "sz_rate": 0.1
+      }
+    },
+    {
+      "timestamp": "2026-02-14T20:00:51.404740",
+      "draw_date": "2026-02-11",
+      "evaluation": {
+        "main": 1,
+        "sz": true,
+        "tip": 5
+      },
+      "avg_matches": {
+        "main": 0.9,
+        "sz_rate": 0.2
+      }
+    },
+    {
+      "timestamp": "2026-02-18T20:00:47.697855",
+      "draw_date": "2026-02-14",
+      "evaluation": {
+        "main": 1,
+        "sz": true,
+        "tip": 4
+      },
+      "avg_matches": {
+        "main": 0.8,
+        "sz_rate": 0.2
+      }
+    },
+    {
+      "timestamp": "2026-02-21T20:00:51.713450",
+      "draw_date": "2026-02-18",
+      "evaluation": {
+        "main": 1,
+        "sz": false,
+        "tip": 2
+      },
+      "avg_matches": {
+        "main": 0.5,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-02-25T20:00:24.757445",
+      "draw_date": "2026-02-21",
+      "evaluation": {
+        "main": 3,
+        "sz": true,
+        "tip": 1
+      },
+      "avg_matches": {
+        "main": 1.1,
+        "sz_rate": 0.5
+      }
+    },
+    {
+      "timestamp": "2026-02-28T20:00:54.216537",
+      "draw_date": "2026-02-25",
+      "evaluation": {
+        "main": 2,
+        "sz": true,
+        "tip": 10
+      },
+      "avg_matches": {
+        "main": 1.0,
+        "sz_rate": 0.4
+      }
+    },
+    {
+      "timestamp": "2026-03-04T20:00:54.207569",
+      "draw_date": "2026-02-28",
+      "evaluation": {
+        "main": 2,
+        "sz": false,
+        "tip": 7
+      },
+      "avg_matches": {
+        "main": 0.5,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-03-07T20:00:54.255644",
+      "draw_date": "2026-03-04",
+      "evaluation": {
+        "main": 1,
+        "sz": true,
+        "tip": 9
+      },
+      "avg_matches": {
+        "main": 0.4,
+        "sz_rate": 0.1
+      }
+    },
+    {
+      "timestamp": "2026-03-11T20:04:25.014685",
+      "draw_date": "2026-03-07",
+      "evaluation": {
+        "main": 3,
+        "sz": false,
+        "tip": 7
+      },
+      "avg_matches": {
+        "main": 0.9,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-03-14T20:00:53.783538",
+      "draw_date": "2026-03-11",
+      "evaluation": {
+        "main": 3,
+        "sz": false,
+        "tip": 6
+      },
+      "avg_matches": {
+        "main": 1.5,
+        "sz_rate": 0.1
+      }
+    },
+    {
+      "timestamp": "2026-03-18T20:00:49.938872",
+      "draw_date": "2026-03-14",
+      "evaluation": {
+        "main": 2,
+        "sz": false,
+        "tip": 2
+      },
+      "avg_matches": {
+        "main": 0.7,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-03-21T20:00:47.286207",
+      "draw_date": "2026-03-18",
+      "evaluation": {
+        "main": 3,
+        "sz": false,
+        "tip": 7
+      },
+      "avg_matches": {
+        "main": 1.3,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-03-26T09:10:14.208620",
+      "draw_date": "2026-03-21",
+      "evaluation": {
+        "main": 2,
+        "sz": false,
+        "tip": 10
+      },
+      "avg_matches": {
+        "main": 0.2,
+        "sz_rate": 0.1
+      }
+    },
+    {
+      "timestamp": "2026-03-28T20:00:55.831816",
+      "draw_date": "2026-03-25",
+      "evaluation": {
+        "main": 3,
+        "sz": false,
+        "tip": 2
+      },
+      "avg_matches": {
+        "main": 1.9,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-04-01T20:00:53.000438",
+      "draw_date": "2026-03-28",
+      "evaluation": {
+        "main": 1,
+        "sz": false,
+        "tip": 1
+      },
+      "avg_matches": {
+        "main": 0.6,
+        "sz_rate": 0.1
+      }
+    },
+    {
+      "timestamp": "2026-04-04T20:54:46.885784",
+      "draw_date": "2026-04-01",
+      "evaluation": {
+        "main": 2,
+        "sz": false,
+        "tip": 3
+      },
+      "avg_matches": {
+        "main": 1.0,
+        "sz_rate": 0.1
+      }
+    },
+    {
+      "timestamp": "2026-04-08T20:00:54.635015",
+      "draw_date": "2026-04-04",
+      "evaluation": {
+        "main": 1,
+        "sz": false,
+        "tip": 1
+      },
+      "avg_matches": {
+        "main": 0.5,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-04-11T20:00:52.934246",
+      "draw_date": "2026-04-08",
+      "evaluation": {
+        "main": 1,
+        "sz": true,
+        "tip": 1
+      },
+      "avg_matches": {
+        "main": 0.9,
+        "sz_rate": 0.4
+      }
+    },
+    {
+      "timestamp": "2026-04-15T20:07:32.209888",
+      "draw_date": "2026-04-11",
+      "evaluation": {
+        "main": 2,
+        "sz": false,
+        "tip": 2
+      },
+      "avg_matches": {
+        "main": 1.2,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-04-18T20:05:26.251241",
+      "draw_date": "2026-04-15",
+      "evaluation": {
+        "main": 1,
+        "sz": false,
+        "tip": 7
+      },
+      "avg_matches": {
+        "main": 0.1,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-04-22T20:11:15.133475",
+      "draw_date": "2026-04-18",
+      "evaluation": {
+        "main": 0,
+        "sz": false,
+        "tip": null
+      },
+      "avg_matches": {
+        "main": 0.0,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-04-25T20:12:51.557882",
+      "draw_date": "2026-04-22",
+      "evaluation": {
+        "main": 2,
+        "sz": false,
+        "tip": 4
+      },
+      "avg_matches": {
+        "main": 1.0,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-04-29T20:00:54.738036",
+      "draw_date": "2026-04-25",
+      "evaluation": {
+        "main": 3,
+        "sz": false,
+        "tip": 5
+      },
+      "avg_matches": {
+        "main": 1.5,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-05-02T20:05:10.517397",
+      "draw_date": "2026-04-29",
+      "evaluation": {
+        "main": 1,
+        "sz": false,
+        "tip": 3
+      },
+      "avg_matches": {
+        "main": 0.2,
+        "sz_rate": 0.1
+      }
+    },
+    {
+      "timestamp": "2026-05-06T20:00:51.391264",
+      "draw_date": "2026-05-02",
+      "evaluation": {
+        "main": 3,
+        "sz": false,
+        "tip": 7
+      },
+      "avg_matches": {
+        "main": 1.2,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-05-09T21:16:17.020494",
+      "draw_date": "2026-05-06",
+      "evaluation": {
+        "main": 1,
+        "sz": false,
+        "tip": 2
+      },
+      "avg_matches": {
+        "main": 0.1,
+        "sz_rate": 0.1
+      }
+    },
+    {
+      "timestamp": "2026-05-13T20:00:57.516757",
+      "draw_date": "2026-05-09",
+      "evaluation": {
+        "main": 1,
+        "sz": false,
+        "tip": 6
+      },
+      "avg_matches": {
+        "main": 0.3,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-05-16T20:00:49.739335",
+      "draw_date": "2026-05-13",
+      "evaluation": {
+        "main": 1,
+        "sz": false,
+        "tip": 2
+      },
+      "avg_matches": {
+        "main": 0.2,
+        "sz_rate": 0.1
+      }
+    },
+    {
+      "timestamp": "2026-05-19T10:53:15.548204",
+      "draw_date": "2026-05-16",
+      "evaluation": {
+        "main": 2,
+        "sz": false,
+        "tip": 7
+      },
+      "avg_matches": {
+        "main": 0.9,
+        "sz_rate": 0.0
+      }
+    },
+    {
+      "timestamp": "2026-05-19T12:56:08.782697",
+      "draw_date": "2026-01-07",
+      "evaluation": {
+        "main": 0,
+        "sz": false
+      },
+      "avg_matches": {
+        "main": 0.0
+      },
+      "note": "retroactive_learning"
     }
   ]
 }
\ No newline at end of file
diff --git a/data/ultimate_ml_models/deep_learning/lstm_config_49.json b/data/ultimate_ml_models/deep_learning/lstm_config_49.json
index 3d3f76d..6d9e8a2 100644
--- a/data/ultimate_ml_models/deep_learning/lstm_config_49.json
+++ b/data/ultimate_ml_models/deep_learning/lstm_config_49.json
@@ -1,9 +1,9 @@
 {
-  "trained_at": "2026-02-04T09:51:16.756987",
-  "num_samples": 3076,
+  "trained_at": "2026-05-19T12:56:08.778673",
+  "num_samples": 3106,
   "num_features": 20,
-  "final_loss": 0.3723479768672547,
-  "final_val_loss": 0.3735503777861595,
-  "best_val_loss": 0.3733456790447235,
+  "final_loss": 0.3726997012511278,
+  "final_val_loss": 0.37363722175359726,
+  "best_val_loss": 0.373420712351799,
   "epochs_trained": 30
 }
\ No newline at end of file
diff --git a/data/ultimate_ml_models/deep_learning/lstm_model_49.pth b/data/ultimate_ml_models/deep_learning/lstm_model_49.pth
index 388d28b..7be9924 100644
Binary files a/data/ultimate_ml_models/deep_learning/lstm_model_49.pth and b/data/ultimate_ml_models/deep_learning/lstm_model_49.pth differ
diff --git a/data/ultimate_ml_models/learning_state.json b/data/ultimate_ml_models/learning_state.json
index 5e87dcb..34da5ee 100644
--- a/data/ultimate_ml_models/learning_state.json
+++ b/data/ultimate_ml_models/learning_state.json
@@ -1,61 +1,61 @@
 {
   "adjustments": {
-    "1": -0.019239457546212986,
-    "2": -0.04864542018655696,
-    "3": -0.0341626104844147,
-    "4": -0.019313709421212986,
-    "5": -0.03386929706155697,
-    "6": -0.04864542018655696,
-    "7": 0.009509281782781966,
-    "8": -0.01982426680905131,
-    "9": -0.019164832546212984,
-    "10": -0.019458901407925413,
-    "11": -0.0192376104844147,
-    "12": -0.005193716018053124,
-    "13": -0.034089832546212985,
-    "14": -0.04864542018655696,
-    "15": -0.03386929706155697,
-    "16": -0.0341626104844147,
-    "17": -0.04864542018655696,
-    "18": -0.03401668888972884,
-    "19": -0.04864542018655696,
-    "20": -0.04864542018655696,
-    "21": -0.019314446380353845,
-    "22": -0.03394317767718197,
-    "23": -0.019750036932742264,
-    "24": -0.03386929706155697,
-    "25": -0.004753345214365449,
-    "26": -0.03401668888972884,
-    "27": -0.019458901407925413,
-    "28": -0.019384649532925416,
-    "29": -0.034089832546212985,
-    "30": -0.04864542018655696,
-    "31": -0.04864542018655696,
-    "32": -0.005190049554206994,
-    "33": -0.034378768229570394,
-    "34": -0.04864542018655696,
-    "35": -0.03372042018655696,
-    "36": -0.04864542018655696,
-    "37": -0.004679834001818573,
-    "38": -0.03423502453292542,
-    "39": -0.03430707651119357,
-    "40": -0.034378768229570394,
-    "41": -0.04864542018655696,
-    "42": -0.034378768229570394,
-    "43": -0.04864542018655696,
-    "44": -0.03372042018655696,
-    "45": -0.04864542018655696,
-    "46": -0.005049972321408152,
-    "47": -0.03379504518655696,
-    "48": -0.03401668888972884,
-    "49": -0.019092802677181973
+    "1": -0.0994862945437695,
+    "2": -0.1248629636841759,
+    "3": -0.12616662253783967,
+    "4": -0.15553493931812296,
+    "5": -0.11189041747698655,
+    "6": -0.1388683136503966,
+    "7": -0.09014676347906732,
+    "8": -0.11572166445504231,
+    "9": -0.07520215115747134,
+    "10": -0.10010115549147716,
+    "11": -0.11560963436741567,
+    "12": -0.10028342051734862,
+    "13": -0.11168978861557464,
+    "14": -0.1526636856874924,
+    "15": -0.05417950645156993,
+    "16": -0.12777928265967228,
+    "17": -0.12530654686312348,
+    "18": -0.11183229142514102,
+    "19": -0.09902207172091577,
+    "20": -0.029776650961084578,
+    "21": -0.12733768488517044,
+    "22": -0.14123268787172502,
+    "23": -0.1135369674174259,
+    "24": -0.1269362504093053,
+    "25": -0.08791477391266757,
+    "26": -0.1253552225691296,
+    "27": -0.128343701675931,
+    "28": -0.08632929916101496,
+    "29": -0.09930392741748621,
+    "30": -0.15362771006530596,
+    "31": -0.1659211045824391,
+    "32": -0.07242761451468395,
+    "33": -0.12702118870091922,
+    "34": -0.1383242826775991,
+    "35": -0.11176200966803025,
+    "36": -0.13694601435372344,
+    "37": -0.047805930390573126,
+    "38": -0.14016944903534453,
+    "39": -0.12692425715858557,
+    "40": -0.09995688206616946,
+    "41": -0.16727016816434043,
+    "42": -0.1259060956242059,
+    "43": -0.09600747206120991,
+    "44": -0.11335461843807568,
+    "45": -0.15376749982199803,
+    "46": -0.10192355718548886,
+    "47": -0.12410346839445828,
+    "48": -0.09794025493170301,
+    "49": -0.1003416088372136
   },
   "stats": {
-    "incorrect": 430,
-    "correct": 60,
-    "cycles": 10,
-    "last_update": "2026-01-31T20:12:26.724555"
+    "incorrect": 1720,
+    "correct": 240,
+    "cycles": 40,
+    "last_update": "2026-05-19T12:56:08.782124"
   },
   "learning_rate": 0.1,
-  "last_saved": "2026-01-31T20:12:26.724608"
+  "last_saved": "2026-05-19T12:56:08.782183"
 }
\ No newline at end of file
diff --git a/data/ultimate_ml_models/trained_models.pkl b/data/ultimate_ml_models/trained_models.pkl
index bfceff7..8b0ab42 100644
Binary files a/data/ultimate_ml_models/trained_models.pkl and b/data/ultimate_ml_models/trained_models.pkl differ
diff --git a/scripts/generators/ultimate_ai_ml_hybrid_generator.py b/scripts/generators/ultimate_ai_ml_hybrid_generator.py
index ccf73be..234b42e 100644
--- a/scripts/generators/ultimate_ai_ml_hybrid_generator.py
+++ b/scripts/generators/ultimate_ai_ml_hybrid_generator.py
@@ -146,6 +146,9 @@ class UltimateAIMLHybridGenerator:
         # 6. Initialize Real-Time Learning
         print("📚 Activating Real-Time Learning...", end=" ", flush=True)
         self.real_time_learner.initialize(self.features_df)
+        _counts = self.df[['Z1','Z2','Z3','Z4','Z5','Z6']].stack().value_counts()
+        freq = {n: int(_counts.get(n, 0)) for n in range(1, 50)}
+        self.real_time_learner.set_frequency_prior(freq)
         print("✅")
         
         self.is_trained = self.ai_ml_engine.is_trained
@@ -230,6 +233,19 @@ class UltimateAIMLHybridGenerator:
             tip_counter += len(tips)
             print(f"✅ ({count} tips)")
         
+        # Strukturfilter: Summe + Parität korrigieren
+        fixed_count = 0
+        for tip in all_tips:
+            if not self._passes_structural_constraints(tip['numbers']):
+                tip['numbers'] = self._apply_structural_fix(tip['numbers'], ai_predictions)
+                tip['ai_score'] = np.mean([ai_predictions.get(n, 0.1) for n in tip['numbers']])
+                tip['pattern_weight'] = self.pattern_engine.calculate_pattern_weight(tip['numbers'])
+                tip['confidence'] = (tip['ai_score'] + tip['pattern_weight']) / 2
+                tip['quality'] = self._calculate_quality_score(tip['numbers'], ai_predictions, tip['pattern_weight'])
+                fixed_count += 1
+        if fixed_count:
+            print(f"   🔧 {fixed_count} Tip(s) via Strukturfilter korrigiert (Summe/Parität)")
+
         # Output all tips
         print(f"\n📋 RESULTS:")
         print("=" * 95)
@@ -406,29 +422,21 @@ class UltimateAIMLHybridGenerator:
         
         selected = []
         for position in range(6):
-            best_candidate = None
-            best_score = -1
-            
-            for candidate in all_candidates:
-                if candidate not in selected:
-                    ai_s = ai_predictions.get(candidate, 0.1)
-                    pattern_s = self.pattern_engine.get_number_pattern_score(candidate)
-                    diversity_s = self._calculate_diversity_score(candidate, selected) if selected else 0.5
-                    
-                    ensemble_score = (ai_s * 0.4 + pattern_s * 0.3 + diversity_s * 0.3)
-                    
-                    if ensemble_score > best_score:
-                        best_score = ensemble_score
-                        best_candidate = candidate
-            
-            if best_candidate:
-                selected.append(best_candidate)
-            else:
-                available = [n for n in range(1, 50) if n not in selected]
-                if available:
-                    selected.append(random.choice(available))
-        
-        selected = sorted(selected[:6])
+            candidates = [c for c in all_candidates if c not in selected]
+            if not candidates:
+                candidates = [n for n in range(1, 50) if n not in selected]
+
+            scores = []
+            for c in candidates:
+                ai_s = ai_predictions.get(c, 0.1)
+                pattern_s = self.pattern_engine.get_number_pattern_score(c)
+                diversity_s = self._calculate_diversity_score(c, selected) if selected else 0.5
+                scores.append(max(0.001, ai_s * 0.4 + pattern_s * 0.3 + diversity_s * 0.3))
+
+            choice = random.choices(candidates, weights=scores)[0]
+            selected.append(choice)
+
+        selected = sorted(selected)
         superzahl = self._get_smart_superzahl(tip_number)
         
         ai_score = np.mean([ai_predictions.get(n, 0.1) for n in selected])
@@ -447,6 +455,55 @@ class UltimateAIMLHybridGenerator:
             'quality': quality
         }
     
+    def _passes_structural_constraints(self, numbers):
+        """Prüft Summenbereich (122-176) und Parität (mind. 1G + 1U)."""
+        s = sum(numbers)
+        if s < 100 or s > 200:
+            return False
+        even = sum(1 for n in numbers if n % 2 == 0)
+        if even == 0 or even == 6:
+            return False
+        return True
+
+    def _apply_structural_fix(self, numbers, ai_preds):
+        """Korrigiert Summe/Parität durch minimalen Tausch."""
+        nums = list(numbers)
+        even = [n for n in nums if n % 2 == 0]
+        odd  = [n for n in nums if n % 2 != 0]
+        if len(even) == 0:
+            worst = min(odd, key=lambda n: ai_preds.get(n, 0))
+            cands = sorted([n for n in range(2, 50, 2) if n not in nums],
+                           key=lambda n: -ai_preds.get(n, 0))
+            if cands:
+                nums.remove(worst)
+                nums.append(cands[0])
+        elif len(odd) == 0:
+            worst = min(even, key=lambda n: ai_preds.get(n, 0))
+            cands = sorted([n for n in range(1, 50, 2) if n not in nums],
+                           key=lambda n: -ai_preds.get(n, 0))
+            if cands:
+                nums.remove(worst)
+                nums.append(cands[0])
+        for _ in range(10):
+            s = sum(nums)
+            if 100 <= s <= 200:
+                break
+            if s > 200:
+                highest = max(nums)
+                cands = sorted([n for n in range(1, highest) if n not in nums],
+                               key=lambda n: -ai_preds.get(n, 0))
+                if cands:
+                    nums.remove(highest)
+                    nums.append(cands[0])
+            else:
+                lowest = min(nums)
+                cands = sorted([n for n in range(lowest + 1, 50) if n not in nums],
+                               key=lambda n: -ai_preds.get(n, 0))
+                if cands:
+                    nums.remove(lowest)
+                    nums.append(cands[0])
+        return sorted(nums)
+
     def _calculate_diversity_score(self, candidate, selected):
         """Berechnet Diversitäts-Score."""
         if not selected:
@@ -1295,6 +1352,8 @@ class RealTimeLearner:
         self.stats = defaultdict(int)
         self.cache_path = cache_path
         self.learning_state_file = os.path.join(cache_path, 'learning_state.json') if cache_path else None
+        self.freq_prior = {}
+        self.freq_alpha = 0.2
 
         # Lade gespeicherten State
         if self.learning_state_file and os.path.exists(self.learning_state_file):
@@ -1304,14 +1363,24 @@ class RealTimeLearner:
         """Initialisiert Learning."""
         self.features_df = features_df
 
-    def adjust_predictions(self, predictions):
-        """Passt Predictions an."""
-        adjusted = {}
+    def set_frequency_prior(self, freq):
+        """Setzt Langzeit-Frequenz als Dämpfer (normalisiert auf [0,1])."""
+        max_val = max(freq.values(), default=0)
+        norm = max_val if max_val > 0 else 1
+        self.freq_prior = {n: v / norm for n, v in freq.items()}
 
+    def adjust_predictions(self, predictions):
+        """Passt Predictions an, gedämpft durch Langzeit-Frequenz."""
+        adjusted = {}
         for number, pred in predictions.items():
             adjustment = self.adjustments.get(number, 0)
-            adjusted[number] = np.clip(pred + adjustment * self.learning_rate, 0, 1)
-
+            learner_val = np.clip(pred + adjustment * self.learning_rate, 0, 1)
+            if self.freq_prior:
+                alpha = max(0.0, min(1.0, self.freq_alpha))
+                freq_val = self.freq_prior.get(number, 0.5)
+                adjusted[number] = np.clip((1 - alpha) * learner_val + alpha * freq_val, 0, 1)
+            else:
+                adjusted[number] = learner_val
         return adjusted
 
     def learn_from_result(self, drawing):