Journal of Property Tax Assessment & Administration


Prediction accuracy for mass appraisal has evolved substantially over the last few decades, facilitated by the revolution in data availability and the advancement of computational software. Accompanying these advances, newer geospatial approaches and machine learning algorithms have opened up new horizons for price prediction and mass appraisal assessment. The application of machine learning (ML) and artificial intelligence (AI) within mass appraisal has generated considerable debate; these methods are often perceived as impractical because their explainability and defensibility—required for assessment application, notably in challenge scenarios—are limited. This study compares a traditional multiple regression analysis (MRA) approach with regularized (penalized) machine learning approaches and a more nuanced geostatistical technique, the eigenvector spatial filter (ESF) approach, applying data sets for two urban residential areas in the United Kingdom and the United States. The findings show the efficacy of the geostatistical ESF technique against the ML approaches—both of which outperform the traditional MRA. The findings also show the ESF approach provides the basis of a more understandable alternative spatial method for mass appraisal aligned with the MRA approach, with the spatial filters easily incorporated as predictors into MRA to alleviate spatial autocorrelation. Further, the penalized ML regression approaches offer a more practical alternative to other forms of ML for assessors. Both methods produce reliable yet understandable regression models for mass appraisal assessment.


Artificial intelligence; Valuation approaches; Machine learning; Valuation - Mathematical models