Automated Valuation Services: A case study for Aberdeen in Scotland

Rainer Schulz; Martin Wersing

doi:10.1080/09599916.2020.1861066

Automated Valuation Services: A case study for Aberdeen in Scotland

Rainer Schulz
, Martin Wersing^* (Corresponding Author)

^*Corresponding author for this work

Research output: Contribution to journal › Article › peer-review

5 Citations (Scopus)

10 Downloads (Pure)

Abstract

Automated valuation services (AVSs) offered by listings platforms predict market values based on property characteristics supplied by users. We investigate the implementation of such a service for the City of Aberdeen. We fit different market value models with machine learning methods and assess them in a rolling windows procedure that mimics an AVS setting. We also investigate the ease and robustness with which the models can be implemented. We discuss how prediction uncertainty can be measured and reported to users. If implemented in the future, such a service has the potential to improve the transparency of the local housing market.

Original language	English
Pages (from-to)	154-172
Number of pages	20
Journal	Journal of Property Research
Volume	38
Issue number	2
Early online date	1 Mar 2021
DOIs	https://doi.org/10.1080/09599916.2020.1861066
Publication status	Published - 2021

Bibliographical note

Acknowledgements:
We are grateful to the three anonymous referees and the editor of the journal
for suggestions and comments that helped to improve the paper. We thank
seminar participants at the Technische Universit¨at Berlin, Fiona Stoddard,
and Verity Watson for helpful comments. The usual disclaimer applies.

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 11 Sustainable Cities and Communities

Keywords

housing market
machine learning

Access to Document

10.1080/09599916.2020.1861066Licence: Unspecified

Schulz_et_al_JPR_AutomatedValuationServices_AAM
This is an Accepted Manuscript of an article published by Taylor & Francis in on Journal of Property Research 1 of March 2021, available online: https://www.tandfonline.com/doi/full/10.1080/09599916.2020.1861066
Accepted author manuscript, 406 KBLicence: Unspecified

Cite this

@article{0369392af5e84692b7a34da4e53f3c16,

title = "Automated Valuation Services: A case study for Aberdeen in Scotland",

abstract = "Automated valuation services (AVSs) offered by listings platforms predict market values based on property characteristics supplied by users. We investigate the implementation of such a service for the City of Aberdeen. We fit different market value models with machine learning methods and assess them in a rolling windows procedure that mimics an AVS setting. We also investigate the ease and robustness with which the models can be implemented. We discuss how prediction uncertainty can be measured and reported to users. If implemented in the future, such a service has the potential to improve the transparency of the local housing market. ",

keywords = "housing market, machine learning",

author = "Rainer Schulz and Martin Wersing",

note = "Acknowledgements: We are grateful to the three anonymous referees and the editor of the journal for suggestions and comments that helped to improve the paper. We thank seminar participants at the Technische Universit¨at Berlin, Fiona Stoddard, and Verity Watson for helpful comments. The usual disclaimer applies.",

year = "2021",

doi = "10.1080/09599916.2020.1861066",

language = "English",

volume = "38",

pages = "154--172",

journal = "Journal of Property Research",

issn = "0959-9916",

publisher = "Routledge",

number = "2",

}

TY - JOUR

T1 - Automated Valuation Services

T2 - A case study for Aberdeen in Scotland

AU - Schulz, Rainer

AU - Wersing, Martin

N1 - Acknowledgements: We are grateful to the three anonymous referees and the editor of the journal for suggestions and comments that helped to improve the paper. We thank seminar participants at the Technische Universit¨at Berlin, Fiona Stoddard, and Verity Watson for helpful comments. The usual disclaimer applies.

PY - 2021

Y1 - 2021

N2 - Automated valuation services (AVSs) offered by listings platforms predict market values based on property characteristics supplied by users. We investigate the implementation of such a service for the City of Aberdeen. We fit different market value models with machine learning methods and assess them in a rolling windows procedure that mimics an AVS setting. We also investigate the ease and robustness with which the models can be implemented. We discuss how prediction uncertainty can be measured and reported to users. If implemented in the future, such a service has the potential to improve the transparency of the local housing market.

AB - Automated valuation services (AVSs) offered by listings platforms predict market values based on property characteristics supplied by users. We investigate the implementation of such a service for the City of Aberdeen. We fit different market value models with machine learning methods and assess them in a rolling windows procedure that mimics an AVS setting. We also investigate the ease and robustness with which the models can be implemented. We discuss how prediction uncertainty can be measured and reported to users. If implemented in the future, such a service has the potential to improve the transparency of the local housing market.

KW - housing market

KW - machine learning

U2 - 10.1080/09599916.2020.1861066

DO - 10.1080/09599916.2020.1861066

M3 - Article

SN - 0959-9916

VL - 38

SP - 154

EP - 172

JO - Journal of Property Research

JF - Journal of Property Research

IS - 2

ER -

Automated Valuation Services: A case study for Aberdeen in Scotland

Abstract

Bibliographical note

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this