{
    "model_name": "Housing Price Prediction Linear Regression Model",
    "model_type": "Regression",
    "algorithm": {
        "name": "Linear Regression",
        "library": "scikit-learn",
        "version": "1.0"
    },
    "training_dataset": {
        "name": "Housing Price Dataset",
        "description": "Structured housing data containing property size, number of rooms, construction year, city, country, and listing price.",
        "doi": "To be added after dataset deposit"
    },
    "input_features": [
        "property_size_m2",
        "total_rooms",
        "construction_year"
    ],
    "target_variable": "listing_price_eur",
    "hyperparameters": {
        "fit_intercept": true,
        "copy_X": true,
        "positive": false
    },
    "evaluation_metrics": {
        "mean_absolute_error": 18200.11,
        "root_mean_squared_error": 24500.42,
        "r2_score": 0.87
    },
    "intended_use": "Educational FAIR data science demonstration for reproducible housing price prediction.",
    "limitations": "The model is a baseline regression model and does not include advanced real estate market factors such as neighborhood quality, interest rates, energy efficiency, or exact geographic coordinates.",
    "ethical_considerations": "The model should not be used for financial, legal, mortgage, or real-world property valuation decisions.",
    "related_files": {
        "model_card": "docs/model-card.md",
        "training_script": "src/training/train_model.py",
        "evaluation_script": "src/evaluation/evaluate_model.py",
        "model_artifact": "outputs/model.pkl"
    }
}