1{"record_id": "a072fb43e67fcc553e457777f0c68324ace19eb7", "eligible": true, "short_ref": "Zhong (2024)", "country": "United States (per paper; Kaggle 'Housing Price Prediction' dataset of unstated origin)", "city": null, "property_type": "houses", "price_type": "listed/transaction price (unspecified, Kaggle)", "n_obs": 545,2 "sample_period": null, "data_source": "Kaggle 'Housing Price Prediction' dataset (Harish Kumar, 2023)", "methods_compared": ["OLS multiple linear regression (log price)", "random forest"],3 "best_method": "OLS multiple linear regression", "metric": "RMSE", "best_value": 0.2032158, "hedonic_value": 0.2032158,4 "test_set": "unknown", "features_ai": "none",5 "incremental_ai_gain": null, "incremental_ai_metric": "", "marginal_effects": "coefficients", "notes": "Table 3: MLRM RMSE 0.2032158 / MAPE 0.0103682 vs RF RMSE 0.2094694 / MAPE 0.0107626 (dependent variable is log housing price, so RMSE is in log units and MAPE is a fraction of log price). The OLS hedonic is itself the best model, so hedonic_value equals best_value. No train/test split is described (544 obs after IQR outlier removal), so test-set design is unknown. Multiple R2 of the OLS = 0.697 (adjusted 0.6896). Conference proceedings, very small sample.", "confidence": "medium"}6