baseline_experiments:
  - name: "bigru"
    description: "Baseline BiGRU with full name features"
    model_type: "bigru"
    features: [ "full_name" ]
    model_params:
      max_len: 20
      embedding_dim: 64
      gru_units: 32
      epochs: 2
      batch_size: 32
    tags: [ "baseline", "neural", "bigru" ]

  - name: "cnn"
    description: "Baseline CNN with character patterns"
    model_type: "cnn"
    features: [ "full_name" ]
    model_params:
      max_len: 20
      embedding_dim: 64
      filters: 64
      kernel_size: 3
      dropout: 0.5
      epochs: 2
      batch_size: 32
    tags: [ "baseline", "neural", "cnn" ]

  - name: "ensemble"
    description: "Baseline Ensemble with multiple models"
    model_type: "ensemble"
    features: [ "full_name", "name_length", "word_count" ]
    model_params:
      base_models: [ "logistic_regression", "random_forest", "xgboost" ]
      voting: "soft"
      cv_folds: 5
    tags: [ "baseline", "ensemble" ]

  - name: "lightgbm"
    description: "Baseline LightGBM with engineered features"
    model_type: "lightgbm"
    features: [ "full_name", "name_length", "word_count" ]
    model_params:
      n_estimators: 100
      max_depth: -1
      learning_rate: 0.1
      num_leaves: 31
      subsample: 0.8
      colsample_bytree: 0.8
    tags: [ "baseline", "lightgbm" ]

  - name: "logistic_regression_fullname"
    description: "Baseline logistic regression with full name"
    model_type: "logistic_regression"
    features: [ "full_name" ]
    model_params:
      max_features: 10000
    tags: [ "baseline", "logistic_regression", "fullname" ]

  - name: "logistic_regression_native"
    description: "Logistic regression with native name only"
    model_type: "logistic_regression"
    features: [ "native_name" ]
    model_params:
      max_features: 5000
    tags: [ "baseline", "logistic_regression", "native" ]

  - name: "logistic_regression_surname"
    description: "Logistic regression with surname name only"
    model_type: "logistic_regression"
    features: [ "surname" ]
    model_params:
      max_features: 5000
    tags: [ "baseline", "logistic_regression", "surname" ]

  - name: "lstm"
    description: "Baseline LSTM with full name features"
    model_type: "lstm"
    features: [ "full_name" ]
    model_params:
      embedding_dim: 128
      lstm_units: 64
      epochs: 2
      batch_size: 64
    tags: [ "baseline", "neural", "lstm" ]

  - name: "naive_bayes"
    description: "Baseline Naive Bayes with full name features"
    model_type: "naive_bayes"
    features: [ "full_name" ]
    model_params:
      max_features: 5000
    tags: [ "baseline", "naive_bayes" ]

  - name: "random_forest"
    description: "Baseline Random Forest with engineered features"
    model_type: "random_forest"
    features: [ "name_length", "word_count", "province" ]
    model_params:
      n_estimators: 100
      max_depth: 10
      min_samples_split: 2
      min_samples_leaf: 1
    tags: [ "baseline", "random_forest", "engineered" ]

  - name: "svm"
    description: "Baseline SVM with full name features"
    model_type: "svm"
    features: [ "full_name" ]
    model_params:
      C: 1.0
      kernel: "rbf"
      ngram_range: [ 2, 4 ]
      max_features: 5000
    tags: [ "baseline", "svm" ]

  - name: "transformer"
    description: "Baseline Transformer with attention mechanism"
    model_type: "transformer"
    features: [ "full_name" ]
    model_params:
      embedding_dim: 128
      num_heads: 4
      num_layers: 2
      epochs: 2
      batch_size: 64
    tags: [ "baseline", "neural", "transformer" ]

  - name: "xgboost"
    description: "Baseline XGBoost with engineered features"
    model_type: "xgboost"
    features: [ "full_name", "name_length", "word_count" ]
    model_params:
      n_estimators: 100
      max_depth: 6
      learning_rate: 0.1
      subsample: 0.8
      colsample_bytree: 0.8
    tags: [ "baseline", "xgboost" ]


# Advanced Experiments Configuration
advanced_experiments:

# Feature Study Configurations
feature_studies:

# Hyperparameter Tuning Configurations
hyperparameter_tuning: