1{"record_id": "a483774defcbadf7676aaa742f594af28562b13a", "eligible": true, "short_ref": "Lenaers, Boudt & De Moor (2023)", "country": "Belgium", "city": "Belgium (national, private dataset)", "property_type": "residential properties (rentals)", "price_type": "monthly gross rent (agent estimates, indexed to 2019 EUR)", "n_obs": 18935,2 "sample_period": "2019-01-01 to 2022-05-04", "data_source": "Private dataset from a Belgian real estate player (agent rent estimates) + OpenStreetMap POI features", "methods_compared": ["linear regression (OLS)", "random forest", "XGBoost"],3 "best_method": "XGBoost", "metric": "MAPE", "best_value": 10.33, "hedonic_value": 11.59,4 "test_set": "holdout", "features_ai": "none",5 "incremental_ai_gain": null, "incremental_ai_metric": "", "marginal_effects": "SHAP", "notes": "Table II, test set: XGBR MAE 104.68 EUR, RMSE 210.71 EUR, MAPE 10.33%; RFR 110.07/221.95/10.83%; LR 120.82/246.47/11.59%. Models tuned with TPE and 10-fold CV on the train set, evaluated on a holdout test set. Caveat: the logarithm of the indexed asking price is included as a predictor, which inflates accuracy for all models. Interpretation via SHAP feature-importance and SHAP summary plots (asking price and cadastral income dominant).", "confidence": "high"}6