Out-of-Sample House Price Prediction by Hedonic Price Models and Machine Learning Algorithms
19 August 2021
In an illiquid market like the real estate market, market values are not readily available. Transactions are scarce and do not always reflect market value. As a consequence, appraisal values play an important role to inform agents in decision making, financial reporting and for property taxes.
For example, appraisal values are used for property investment decisions and for providing mortgage loans. In a recent report De Nederlandsche Bank raises concerns about the quality and independency of appraisal values (Van der Molen and Nijskens, 2019).
The authors show that one third of all appraisal values exactly match the transaction price, and in almost 60% the appraisal value is higher than the transaction price. Automated valuation models (AVMs) are less prone to potential client influence. However, in order to be accepted by a broad audience, AVMs need to be transparent, robust, explainable and they need to provide reliable predictions. In this research the authors address these issues. They compare traditional hedonic price models to more advanced machine learning algorithms and analyse the accuracy of out-of-sample predictions and variable importance. The research is based on almost all residential transaction prices in the Netherlands in 2017.
Marc Francke, Ortec Finance en University of Amsterdam
Jeroen Beimer, Bouwinvest
Do you have questions about this article or an idea for another interesting analysis? Please contact Marc Francke using the details below.
Daily appraisal of commercial real estate a new mixed frequency approach
We present a mixed frequency repeat sales model for commercial real estate, taking into account changes in net operating income between the date of buying and selling the property. Moreover, we relate monthly private market index asset returns to lags, up to 1 year, of daily (REIT) index returns.
A Machine Learning Approach to Price Indices: Applications in Commercial Real Estate
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.
Ortec Finance 2021 Customer Satisfaction Survey shows very high scores
At Ortec Finance, as part of the processes that we have in place to better understand what our clients think of us, our products, and our services, we conduct an annual customer satisfaction survey in the months of October and November. We are proud to announce that the survey shows very high scores for the fourth year in a row!
Forecasting US Commercial Property Price Indexes Using Dynamic Factor Models
The general purpose of a dynamic factor model (DFM) is to summarize a large number of time series into a few common factors. In this paper Alex van de Minne, Marc Francke and David Geltner explore several DFMs on 80 granular, non-overlapping commercial property price indexes in the US, quarterly from 2001Q1 to 2017Q2.
Commonalities in Private Commercial Real Estate Market Liquidity and Price Index Returns
In this paper Dorinth van Dijk and Marc Francke examine co-movements in private commercial real estate index returns and market liquidity in the US (apartment, office, retail) and for eighteen global cities, using data from Real Capital Analytics over the period 2005–2018.