# Equal tuning budget across information sets. Hyper-parameters are tuned ONLY on the validation period.
baselines:
  B0: {type: base_rate}
  B1: {type: logistic, inputs: [fundamentals, controls]}
  B2: {type: logistic, inputs: [fundamentals, controls, daily]}
  B3: {type: logistic, inputs: [fundamentals, controls, daily, intraday_30m]}
  B4: {type: logistic, inputs: [fundamentals, controls, daily, intraday_5m]}
  B5: {type: logistic, inputs: [fundamentals, controls, daily, intraday_1m]}
logistic:
  penalty: l2
  C_grid: [0.01, 0.03, 0.1, 0.3, 1.0, 3.0]
  standardize: train_only
  impute: train_median
lightgbm:
  information_sets: [B1, B2, B3, B4, B5]
  budget_trials: 24          # identical random-search budget for every information set
  seed: 20261102
  search_space:
    num_leaves: [7, 15, 31, 63]
    learning_rate: [0.01, 0.03, 0.05]
    min_child_samples: [50, 100, 200]
    feature_fraction: [0.5, 0.7, 0.9]
    bagging_fraction: [0.6, 0.8, 1.0]
    lambda_l2: [0.0, 1.0, 10.0]
  n_estimators_max: 2000
  early_stopping_rounds: 100
neural: {enabled: false, reason: "owner instruction 2026-11-02: minimise AI usage; B7/B8 not run"}