Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Forecasting office rents with ensemble models – the case for European real estate markets

Forecasting office rents with ensemble models – the case for European real estate markets Commercial real estate and office rental values, in particular, have long been the focus of research. Several forecasting frameworks for office rental values in multivariate and univariate fashions have been proposed. Recent developments in time series forecasting using machine learning and deep learning methods offer an opportunity to update traditional univariate forecasting frameworks.Design/methodology/approachWith the aim to extend research on univariate rent forecasting a hybrid methodology combining both ARIMA and a neural network model is proposed to exploit the unique strengths of both methods in linear and nonlinear modelling. N-BEATS, a deep learning algorithm that has demonstrated state-of-the-art forecasting performance in major forecasting competitions, are explained. With the ARIMA model, it is jointly applied to the office rental dataset to produce forecasts for four-quarters ahead.FindingsWhen the approach is applied to a dataset of 21 major European office cities, the results show that the ensemble model can be an effective approach to improve the prediction accuracy achieved by each of the models used separately.Practical implicationsReal estate forecasting is essential for assessing the value of managing portfolios and for evaluating investment strategies. The approach applied in this paper confirms the heterogeneity of real estate markets. The application of mixed modelling via linear and nonlinear methods decreases the uncertainty of abrupt changes in rents.Originality/valueTo the best of the authors' knowledge, no such application of a hybrid model updating classical statistical forecasting with a deep learning neural network approach in the field of commercial real estate rent forecasting has been undertaken. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Journal of Property Investment & Finance Emerald Publishing

Forecasting office rents with ensemble models – the case for European real estate markets

Download PDF
26 pages

Loading next page...
 
/lp/emerald-publishing/forecasting-office-rents-with-ensemble-models-the-case-for-european-1WUbsLcSBp
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
1463-578X
DOI
10.1108/jpif-11-2021-0094
Publisher site
See Article on Publisher Site

Abstract

Commercial real estate and office rental values, in particular, have long been the focus of research. Several forecasting frameworks for office rental values in multivariate and univariate fashions have been proposed. Recent developments in time series forecasting using machine learning and deep learning methods offer an opportunity to update traditional univariate forecasting frameworks.Design/methodology/approachWith the aim to extend research on univariate rent forecasting a hybrid methodology combining both ARIMA and a neural network model is proposed to exploit the unique strengths of both methods in linear and nonlinear modelling. N-BEATS, a deep learning algorithm that has demonstrated state-of-the-art forecasting performance in major forecasting competitions, are explained. With the ARIMA model, it is jointly applied to the office rental dataset to produce forecasts for four-quarters ahead.FindingsWhen the approach is applied to a dataset of 21 major European office cities, the results show that the ensemble model can be an effective approach to improve the prediction accuracy achieved by each of the models used separately.Practical implicationsReal estate forecasting is essential for assessing the value of managing portfolios and for evaluating investment strategies. The approach applied in this paper confirms the heterogeneity of real estate markets. The application of mixed modelling via linear and nonlinear methods decreases the uncertainty of abrupt changes in rents.Originality/valueTo the best of the authors' knowledge, no such application of a hybrid model updating classical statistical forecasting with a deep learning neural network approach in the field of commercial real estate rent forecasting has been undertaken.

Journal

Journal of Property Investment & Finance – Emerald Publishing

Published: Mar 27, 2023

Keywords: Commercial real estate; Time series forecasting; Machine learning; Deep learning; Office rent; ARIMA; N-BEATS

References

  • Mass appraisal of residential apartments: an application of Random forest for valuation and a CART-based approach for model diagnostics
    Antipov, E.A.; Pokryshevskaya, E.B.
  • Combining forecasts
    Armstrong, J.S.
  • Why does forecast combination work so well?
    Atiya, A.F.
  • Modelling the commercial property market: an empirical study of the Singapore office market
    Boon Foo, N.G.; Higgins, D.
  • Time series analysis: forecasting and control
    Box, G.E.P.; Geurts, M.; Jenkins, G.M.
  • Asymmetric properties of office rent adjustment
    Brounen, D.; Jennen, M.
  • Local Office Rent Dynamics: a Tale of Ten Cities
    Brounen, D.; Jennen, M.
  • Long-run equilibrium for the greater Paris office market and short-run adjustments
    Bruneau, C.; Cherfouh, S.
  • Spatial effects and non-linearity in hedonic modeling
    Cajias, M.; Ertl, S.
  • An ex post comparative evaluation of office rent prediction models
    Chaplin, R.
  • Predicting real estate rents: walking backwards into the future
    Chaplin, R.
  • Assessing the forecasting performance of regime-switching, ARIMA and GARCH models of house prices
    Crawford, G.W.; Fratantoni, M.C.
  • Application of GAM additive non-linear models to estimate real estate market value
    Dąbrowski, J.; Adamczyk, T.
  • The vacancy rate and rent levels in the commercial office market
    Frew, J.; Jud, D.
  • The development of a simple regional office rent prediction model
    Gardiner, C.; Henneberry, J.
  • A comparative analysis of the major determinants of office rental values in Europe
    Giussani, B.; Hsia, M.; Tsolacos, S.
  • 25 years of time series forecasting
    Gooijer, J.G.de; Hyndman, R.J.
  • Rental price adjustment and investment in the office market
    Hekman, J.S.
  • Estimation of the rental adjustment process
    Hendershott, P.; MacGregor, B.; Tse, R.
  • Explaining real commercial rents using an error correction model with panel data
    Hendershott, P.; MacGregor, B.; White, M.
  • Asymmetric adjustment in the city of London office market
    Hendershott, P.; Lizieri, C.; MacGregor, B.
  • Another look at measures of forecast accuracy
    Hyndman, R.J.; Koehler, A.B.
  • A new metric of absolute percentage error for intermittent demand forecasts
    Kim, S.; Kim, H.
  • Forecasting REITs and stock indices: group method of data handling neural network approach
    Li, R.Y.; Fong, S.; Chong, K.W.
  • Estimation and updating methods for hedonic valuation
    Mayer, M.; Bourassa, S.C.; Hoesli, M.; Scognamiglio, D.
  • Short and long-run rent adjustment in the Dublin office market
    McCartney, J.
  • Forecasting commercial rental values using ARIMA models
    McGough, T.; Tsolacos, S.
  • Forecasting Australia's real house price index: a comparison of time series and machine learning methods
    Milunovich, G.
  • Panel data modelling of prime office rents: a study of 12 major European markets
    Mouzakis, F.; Richards, D.
  • N-beats: neural basis expansion analysis for interpretable time series forecasting
    Oreshkin, B.N.; Carpov, D.; Chapados, N.; Bengio, Y.
  • N-Beats: neural network for mid-term electricity load forecasting
    Oreshkin, B.N.; Dudek, G.; Pełka, P.; Turkina, E.
  • Using machine learning models and actual transaction data for predicting real estate prices
    Pai, P.-F.; Wang, W.-C.
  • Toward a model of the office building sector
    Rosen, K.T.
  • Price adjustment process for rental office space
    Shilling, J.D.; Sirmans, C.F.; Corgel, J.B.
  • A comparison of the forecasting ability of ARIMA models
    Stevenson, S.
  • A comparison of alternative rental forecasting models: empirical tests on the London office market
    Stevenson, S.; McGarth, O.
  • An application of the ARIMA model to real‐estate prices in Hong Kong
    Tse, R.Y.
  • Vacancy rates and the future of office rents
    Wheaton, W.C.; Torto, R.G.
  • Time series forecasting using a hybrid ARIMA and neural network model
    Zhang, G.