Cybergeo (Feb 2016)
Identification of locational influence on real property values using data mining methods
Abstract
The value of real estate is an important matter for municipal authorities, since property tax is one of their main budget sources. Its estimation tends to be a complex process, owing to the diversity of factors affecting it. One of those factors is property location, which embraces the geographic relationship between the property and the surrounding local amenities. Hedonic modelling is frequently applied to estimate the value of a property; to consider the influence of property location within such models, the region under analysis is usually divided into homogeneous areas. This division can introduce a bias (a particular vision) related to the modifiable areal unit problem. Our intent in this paper is to apply data mining techniques to address a possible valuer bias, a particular valuer’s vision, in the current City of Calgary assessment model. Employing the decision tree technique, one locational attribute (Sub-Neighbourhood) was represented by the (x, y) coordinates of the properties, with approximately 96% correct classification with respect to their City of Calgary sub-neighbourhood designation. By adopting the regression tree technique, we show that it is possible to explain approximately 73% variability of the Sale Price attribute, using only the attribute Sub-Neighbourhood or the (x, y) coordinates as input. In general, the results showed a consistent relationship between property value and location. Additionally, the sale price patterns of actual properties do not conform strictly to the politico-administrative units adopted by the city. Those patterns usually cross the unit boundaries limits or are mixed inside a unit. Our results suggest that using a property’s spatial coordinates, instead of political-administrative subdivisions, to express its location, would lead to more accurate results and not incur the possibility of bias.
Keywords
