This article presents a model agnostic methodology for producing property price indices. The motivation to develop this methodology is to include non-linear and non-parametric models, such as Machine Learning (ML), in the pool of algorithms to produce price indices.

The key innovation is the use of individual out-of-time prediction errors to measure price changes. The data used in this study consist of 29,998 commercial real estate transactions in New York, in the period 2000–2019. The results indicate that the prediction accuracy is higher for the ML models compared to linear models. On the other hand, ML algorithms depend more on the data used for calibration; they produce less stable results when applied to small samples and may exhibit estimation bias. Hence, measures to reduce or eliminate bias need to be implemented, taking into consideration the bias and variance trade-off.

Download whitepaper (open access)


  • Felipe D. Calainho, PhD Candidate, University of Amsterdam Business School
  • Alex M. van de Minne, Research Scientist MIT Center for Real Estate
  • Marc K. Francke, University of Amsterdam - Faculty of Economics and Business and Ortec Finance


Do you have questions about this paper or an idea for another interesting analysis?
Please contact Marc Francke using the details below.

Related Insights

Cookies help us improve your website experience.
By using our website, you agree to our use of cookies.