Using geographically weighted regression for housing market segmentation

Abstract

Urban real estate property values are mainly conditioned by several aspects, which can be summarised in two main classes: intrinsic and extrinsic ones. Intrinsic characters are specific goods while extrinsic features are related to a diversity of goods. Therefore, there is an extremely close correlation between ‘rigidity location’ of property (fixed location) and its value. Possibilities offered by recent developments of statistical techniques, principally geographically weighted regression (GWR), in analysing housing market have given a new impetus in mass appraisal of urban property. More particularly, geographically weighted regression has been adopted in analysing housing market, in order to identify homogeneous areas and to define the marginal contribution that a single location (outlined by these areas) gives to the market value of the property. The model has been built on a sample of 280 data, related to the trades of residential real estate units occurred between 2008 and 2010 in the city of Potenza (Basilicata, southern Italy). The results of territory zoning into homogeneous market areas, in addition to the undoubted usefulness in the field of real estate valuations, has useful implications in terms of taxation, programming territorial transformations and checking ongoing or ex post planning decisions.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 61 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.