{"record_id": "4c31e259cf5625db8bd0cbbcae78c68fed2c8164", "eligible": true, "short_ref": "Changro (2026)", "country": "South Korea", "city": "Seongdong-gu (Seoul) and Gangjin-gun (Jeonnam)", "property_type": "benchmark (standard) houses, mostly detached/rowhouse", "price_type": "appraised benchmark price (MOLIT 2024 survey)", "n_obs": 1670,
 "sample_period": "2024", "data_source": "MOLIT benchmark house survey (data.go.kr)", "methods_compared": ["OLS hedonic without text", "OLS hedonic with text embeddings", "XGBoost with text embeddings"],
 "best_method": "XGBoost with text embeddings", "metric": "R2", "best_value": null, "hedonic_value": null,
 "test_set": "holdout", "features_ai": "listing text embeddings",
 "incremental_ai_gain": 0.05, "incremental_ai_metric": "adjusted R2 (OLS, Seongdong-gu 0.508 -> 0.558; Gangjin-gun 0.633 -> 0.751, i.e. +0.118)", "marginal_effects": "SHAP", "notes": "80/20 random split; 763 houses in Seongdong-gu, 907 in Gangjin-gun, modelled separately. Only printed metric is adjusted R2 of the OLS models (Table 4, apparently full-sample fit): 0.508/0.558 (Seongdong) and 0.633/0.751 (Gangjin) without/with two PCA components of OpenAI sentence embeddings of the environmental description. XGB 'best fit' is shown only graphically (Figure 3, test set), no numeric metric printed, so best_value is null. SHAP importance and SHAP dependence plot for embedding component 1; OLS coefficients also reported.", "confidence": "medium"}