Mass appraisal as affordable public policy: Open data and machine learning for mapping urban land values

• Autores: Carranza, Juan Pablo; Piumetto, Mario; Lucca, Carlos; Da Silva, Everton
• Año de publicación: 2022
• Idioma: inglés
• Tipo de recurso: artículo
• Materia: Machine learning; Open data; Mass appraisal; Urban land value
• Institución: Universidad Nacional de Córdoba

Fil: Carranza, Juan Pablo. Universidad Nacional de Córdoba. Facultad de Ciencias Sociales. Instituto de Investigación y Formación en Administración Pública; Argentina.
Fil: Piumetto, Mario. Universidad Nacional de Cordoba. Facultad de Ciencias Exactas, Físicas y Naturales. Centro de Estudios Territoriales; Argentina.
Fil: Lucca, Carlos. Universidad Nacional de Córdoba. Facultad de Ciencias Sociales. Instituto de Investigación y Formación en Administración Pública; Argentina.
Fil: Da Silva, Everton. Universidade Federal de Santa Catarina. Departamento de Geociencias; Brazil.
Updated cadastral land values are a matter of critical importance for local governments: higher revenue ofproperty taxes, more equitable treatment to taxpayers, a fundamental input in the design of public policiesrelated to access to land and housing for the most vulnerable and a key feature in land value capture strategies tofinance public infrastructure, to name just a few public policies that require correct valuations of land. However,in Latin America, outdated cadastral values are common to most cities. The reasons for this can be found in thecomplexity of the mass appraisal process, lack of institutional and fiscal capacity to undertake it and bureaucraticresistance to its implementation.The objective of this paper is to present a mass appraisal methodology that uses only free and open data toachieve robust urban land valuations. Information from the OpenStreetMap Project is used to generate severalland variables. In addition, the Global Human Settlement Layer of the European Commission is used to determinethe level of consolidation of urban sprawl. Land value data were obtained from the Mapa de Valores de Am´ericaLatina, a collaborative initiative that systemizes more than 68,000 data from more than 900 cities.This information is used to train three tree-based machine learning models: Random Forest, Quantile RandomForest and Gradient Boosting Model. The results support the viability of the proposed strategy, simplifying themass appraisal process in terms of costs, time and complexity of the information used.
https://www.sciencedirect.com/journal/land-use-policy/vol/119/suppl/C
info:eu-repo/semantics/publishedVersion
Fil: Carranza, Juan Pablo. Universidad Nacional de Córdoba. Facultad de Ciencias Sociales. Instituto de Investigación y Formación en Administración Pública; Argentina.
Fil: Piumetto, Mario. Universidad Nacional de Cordoba. Facultad de Ciencias Exactas, Físicas y Naturales. Centro de Estudios Territoriales; Argentina.
Fil: Lucca, Carlos. Universidad Nacional de Córdoba. Facultad de Ciencias Sociales. Instituto de Investigación y Formación en Administración Pública; Argentina.
Fil: Da Silva, Everton. Universidade Federal de Santa Catarina. Departamento de Geociencias; Brazil.
Estudios Urbanos (Planeamiento y Desarrollo)