1{"record_id": "5cebf4171ab33d78f1774e47b906013d8103d51a", "eligible": true, "short_ref": "Upadhye, Bhuravane & Khanche (2026)", "country": "USA", "city": "Ames, Iowa", "property_type": "single-family residential (Ames Housing dataset)", "price_type": "sale price (USD)", "n_obs": null, "sample_period": null, "data_source": "Ames Housing dataset (Kaggle) plus property text descriptions said to be derived from listing metadata and agent narratives", "methods_compared": ["linear regression", "random forest", "XGBoost (structured features only)", "SmartPrice (XGBoost + 1-D CNN text embeddings, feature-level fusion)"], "best_method": "XGBoost + CNN text embeddings (SmartPrice)", "metric": "R2", "best_value": 0.92, "hedonic_value": 0.71, "test_set": "holdout", "features_ai": "listing text embeddings", "incremental_ai_gain": 0.03, "incremental_ai_metric": "R2 (0.89 structured-only XGBoost to 0.92 with CNN text embeddings; RMSE 27,880 to 24,930 USD; MAPE 11.6% to 9.8%)", "marginal_effects": "SHAP", "notes": "Table I (test set, 70/15/15 stratified split, 5-fold CV on training set): Linear Regression RMSE 43,920 / MAE 29,210 / R2 0.71 / MAPE 18.7%; RF 31,550 / 20,120 / 0.84 / 13.1%; XGBoost 27,880 / 17,340 / 0.89 / 11.6%; SmartPrice 24,930 / 15,980 / 0.92 / 9.8%. The 'linear regression' baseline is a generic regression, not a hedonic specification with reported coefficients. Caveats: the public Ames dataset contains no free-text descriptions and the paper does not say how its texts were obtained; n_obs and sample period are not printed; only 2 of 5 CV folds are shown; text has tutorial-like wording. Global and local SHAP values reported (feature names anonymised in the plot).", "confidence": "low"}2