1{"record_id": "9bd166858991ed89e221a8fb56169533ad4f2ece", "eligible": true, "short_ref": "Wang et al. (2026a)", "country": "China", "city": "Shanghai (central urban area)", "property_type": "second-hand flat-type apartments in slab blocks", "price_type": "listing price per m2 (yuan)", "n_obs": 7634, "sample_period": "2024", "data_source": "Beike (ke.com) second-hand housing listings; Baidu street-view panoramas (semantic segmentation view indices)", "methods_compared": ["gradient boosted decision trees (GBDT)"], "best_method": "GBDT", "metric": "R2", "best_value": 0.47, "hedonic_value": null, "test_set": "holdout", "features_ai": "street-view CNN", "incremental_ai_gain": null, "incremental_ai_metric": "", "marginal_effects": "PDP", "notes": "Single GBDT model (grid search + 5-fold CV on training data, evaluated on a held-out test set): R2 = 0.47, MAE = 7,052.82, RMSE = 12,968.90 (yuan; mean price 60,178.85 yuan, i.e. per m2). No OLS/hedonic benchmark and no ablation of the street-view variables. Street-view view indices (sky, tree, grass, building, road, sidewalk, land diversity) from semantic segmentation of Baidu panoramas; relative importance and partial dependence plots reported.", "confidence": "high"}2