A spatio-temporal statistical model for property valuation at country-scale with adjustments for regional submarkets

TL;DR

This paper introduces a flexible statistical model for country-wide property valuation that accounts for regional differences and outperforms existing methods, especially in data-sparse areas, by capturing non-linear effects and regional variations.

Contribution

The authors develop a generalized additive model that segments the country into submarkets and models regional differences, improving valuation accuracy over traditional and machine learning models.

Findings

Model achieves high R-squared values across regions.

Outperforms traditional hedonic and machine learning models.

Aligns well with reported inflation figures.

Abstract

Valuing residential property is inherently complex, requiring consideration of numerous environmental, economic, and property-specific factors. These complexities present significant challenges for automated valuation models (AVMs), which are increasingly used to provide objective assessments for property taxation and mortgage financing. The challenge of obtaining accurate and objective valuations for properties at a country level, and not just within major cities, is further compounded by the presence of multiple localised submarkets-spanning urban, suburban, and rural contexts-where property features contribute differently to value. Existing AVMs often struggle in such settings: traditional hedonic regression models lack the flexibility to capture spatial variation, while advanced machine learning approaches demand extensive datasets that are rarely available. In this article, we address these limitations by developing a robust statistical framework for property valuation in the Irish housing market. We segment the country into six submarkets encompassing cities, large towns, and rural areas, and employ a generalized additive model that captures non-linear effects of property characteristics while allowing feature contributions to vary across submarkets. Our approach outperforms both machine learning-based and traditional hedonic regression models, particularly in data-sparse regions. In out-of-sample validation, our model achieves R-squared values of 0.70, 0.84, and 0.83 for rural areas, towns, and Dublin, respectively, compared to 0.52, 0.71, and 0.82 from a random forest benchmark. Furthermore, the temporal dynamics of our model align closely with reported inflation figures for the study period, providing additional validation of its accuracy.