1{2 "record_id": "fe9b5a96e7007d52e9bebe9eaea418541aa3b090",3 "eligible": false,4 "exclusion_reason": "Evolutionary Polynomial Regression (EPR) automated valuation models of log rent for five Italian cities (Milan, Turin, Rome, Naples, Catania; second half of 2019). The fitted equations are sums of multiplicative monomials of several variables raised to exponents (0, 0.5, 1, 2); no separable per-characteristic coefficients, no standard errors, t-statistics or p-values are reported (only CoD/RMSE/MAPE). No extractable hedonic coefficients.",5 "study": {6 "title": "An Automatic Tool for the Determination of Housing Rental Prices: An Analysis of the Italian Context",7 "year": 2021,8 "doi": "10.3390/su14010309",9 "country": "Italy",10 "region_city": "Milan, Turin, Rome, Naples, Catania",11 "sample_start": 2019,12 "sample_end": 2019,13 "property_type": "rental",14 "price_type": "rent",15 "data_source": "Rented residential properties, second half of 2019 (online listings)",16 "document_type": "journal",17 "estimators": [18 "ML_marginal"19 ],20 "spatial_method": "none",21 "time_fe": false,22 "location_fe": false,23 "se_type": "unknown",24 "n_obs_total": null,25 "ai_methods": [26 "evolutionary polynomial regression (EPR)"27 ],28 "notes": "Rent study; dependent variable ln(rental price); Table 2 lists polynomial expressions, Table 3 the variables selected per city. Kept qualitatively for the AI/AVM synthesis (performance metrics only)."29 },30 "models": [],31 "coefficients": []32}