data_preparation_metadata.json

{
  "dataset": {
    "total_days": 3572,
    "date_range": "2010-10-19 to 2024-12-27",
    "features": 13,
    "target": "target_return"
  },
  "split": {
    "train_days": 2821,
    "val_days": 251,
    "test_days": 499,
    "train_pct": 78.97536394176932,
    "val_pct": 7.026875699888017,
    "test_pct": 13.96976483762598
  },
  "features": [
    "hl_range",
    "log_return",
    "spy_return",
    "co_range",
    "return_lag2",
    "return_lag5",
    "volatility_20d",
    "volume_change",
    "day_cos",
    "day_of_week",
    "day_sin",
    "month_cos",
    "rolling_beta"
  ],
  "prophet_regressors": [
    "hl_range",
    "spy_return",
    "volatility_20d",
    "rolling_beta",
    "volume_change",
    "co_range",
    "day_cos",
    "day_sin"
  ],
  "lstm_sequence_length": 60,
  "last_prices": {
    "train": 178.08999633789062,
    "val": 128.41000366210938,
    "test": 257.8299865722656
  },
  "files_created": [
    "feature_scaler.pkl",
    "train_prophet.csv",
    "val_prophet.csv",
    "test_prophet.csv",
    "X_train_lstm.npy",
    "y_train_lstm.npy",
    "X_val_lstm.npy",
    "y_val_lstm.npy",
    "X_test_lstm.npy",
    "y_test_lstm.npy"
  ]
}