1{"record_id": "9544f4ac839e433b51f55da090f58729fbbf9919", "eligible": true, "short_ref": "Hong, Choi & Kim (2020)", "country": "South Korea", "city": "Seoul (Gangnam district)", "property_type": "apartments", "price_type": "transaction price", "n_obs": 16601,2 "sample_period": "2006-2017", "data_source": "Apartment transaction records, Gangnam district (approx. 40% of all 39,564 transactions)", "methods_compared": ["OLS hedonic", "random forest"],3 "best_method": "random forest", "metric": "MAPE", "best_value": 5.482407, "hedonic_value": 19.60567,4 "test_set": "holdout", "features_ai": "none",5 "incremental_ai_gain": null, "incremental_ai_metric": "", "marginal_effects": "none", "notes": "Random 90/10 train/test split, averaged over 10 trials (Table 5). MAPE in %; same table reports R-squared 0.976198 (RF) vs 0.726056 (OLS) and COD 5.48 vs 19.57; hitting rates within 5%: 72.0% vs 17.4%. Only RF variable-importance (Figure 4) is reported, no SHAP/PDP. Text states 16,601 samples in data section but 16,061 in results section.", "confidence": "high"}6