Purpose
The purpose of this paper is to investigate the accuracy and volatility of different methods for estimating and updating hedonic valuation models.
Design/methodology/approach
The authors apply six estimation methods (linear least squares, robust regression, mixed-effects regression, random forests, gradient boosting and neural networks) and two updating methods (moving and extending windows). They use a large and rich data set consisting of over 123,000 single-family houses sold in Switzerland between 2005 and 2017.
Findings
The gradient boosting method yields the greatest accuracy, while the robust method provides the least volatile predictions. There is a clear trade-off across methods depending on whether the goal is to improve accuracy or avoid volatility. The choice between moving and extending windows has only a modest effect on the results.
Originality/value
This paper compares a range of linear and machine learning techniques in the context of moving or extending window scenarios that are used in practice but which have not been considered in prior research. The techniques include robust regression, which has not previously been used in this context. The data updating allows for analysis of the volatility in addition to the accuracy of predictions. The results should prove useful in improving hedonic models used by property tax assessors, mortgage underwriters, valuation firms and regulatory authorities.