Proposal for the mass appraisal of urban land.: Spatial application of the Quantile Regression Forest algorithm.
Knowledge and monitoring land values are necessary for the implementation of public policies and territorial management, as well as a genuine source of resources for local governments. However, the different territorial characteristics and dynamics demand adequate processes and techniques for each r...
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Artículo revista |
| Lenguaje: | Español |
| Publicado: |
Instituto de Investigación de Vivienda y Hábitat
2021
|
| Materias: | |
| Acceso en línea: | https://revistas.unc.edu.ar/index.php/ReViyCi/article/view/35166 |
| Aporte de: |
| Sumario: | Knowledge and monitoring land values are necessary for the implementation of public policies and territorial management, as well as a genuine source of resources for local governments. However, the different territorial characteristics and dynamics demand adequate processes and techniques for each reality. This paper describes the techniques and results obtained for the massive valuation of land in the province of Córdoba, particularly in mountain localities with a tourist profile. The performance of the Quantile Regression Forest machine learning technique is analyzed in terms of the level of accuracy in predicting land value and the resulting value structures are presented. In addition, the main innovation of the proposed technique consists in the possibility of generating a map of the prediction consistency, in terms of the dispersion coefficient at each point of the space. This last feature is considered a key input in the implementation of public policies for the periodic updating of urban land tax values, by informing about possible areas of the city where the results are of higher or lower quality in relation to the surroundings. |
|---|