Automated valuation modelling

A specification exercise

    Research output: Contribution to journalArticle

    10 Citations (Scopus)
    5 Downloads (Pure)

    Abstract

    Market value predictions for residential properties are important for investment decisions and the risk management of households, banks and real estate developers. The increased access to market data has spurred the development and application of Automated Valuation Models (AVMs), which can provide appraisals at low cost. We discuss the stages involved when developing an AVM. By reflecting on our experience with md*immo, an AVM from Berlin, Germany, our paper contributes to an area that has not received much attention in the academic literature. In addition to discussing the main stages of AVM development, we examine empirically the statistical model development and validation step. We find that automated outlier removal is important and that a log model performs best, but only if it accounts for the retransformation problem and heteroscedasticity.
    Original languageEnglish
    Pages (from-to)131-153
    Number of pages23
    JournalJournal of Property Research
    Volume31
    Issue number2
    Early online date31 Oct 2013
    DOIs
    Publication statusPublished - 2014

    Fingerprint

    valuation
    development model
    modeling
    market
    real estate
    outlier
    risk management
    Berlin
    bank
    costs
    prediction
    cost
    experience

    Keywords

    • hedonic regression
    • log transformation
    • predictive performance

    Cite this

    Automated valuation modelling : A specification exercise. / Schulz, Rainer; Wersing, Martin; Werwatz, Axel.

    In: Journal of Property Research, Vol. 31, No. 2, 2014, p. 131-153.

    Research output: Contribution to journalArticle

    @article{18b181782b8941818366934774d3a9ca,
    title = "Automated valuation modelling: A specification exercise",
    abstract = "Market value predictions for residential properties are important for investment decisions and the risk management of households, banks and real estate developers. The increased access to market data has spurred the development and application of Automated Valuation Models (AVMs), which can provide appraisals at low cost. We discuss the stages involved when developing an AVM. By reflecting on our experience with md*immo, an AVM from Berlin, Germany, our paper contributes to an area that has not received much attention in the academic literature. In addition to discussing the main stages of AVM development, we examine empirically the statistical model development and validation step. We find that automated outlier removal is important and that a log model performs best, but only if it accounts for the retransformation problem and heteroscedasticity.",
    keywords = "hedonic regression, log transformation, predictive performance",
    author = "Rainer Schulz and Martin Wersing and Axel Werwatz",
    year = "2014",
    doi = "10.1080/09599916.2013.846930",
    language = "English",
    volume = "31",
    pages = "131--153",
    journal = "Journal of Property Research",
    issn = "0959-9916",
    publisher = "Routledge",
    number = "2",

    }

    TY - JOUR

    T1 - Automated valuation modelling

    T2 - A specification exercise

    AU - Schulz, Rainer

    AU - Wersing, Martin

    AU - Werwatz, Axel

    PY - 2014

    Y1 - 2014

    N2 - Market value predictions for residential properties are important for investment decisions and the risk management of households, banks and real estate developers. The increased access to market data has spurred the development and application of Automated Valuation Models (AVMs), which can provide appraisals at low cost. We discuss the stages involved when developing an AVM. By reflecting on our experience with md*immo, an AVM from Berlin, Germany, our paper contributes to an area that has not received much attention in the academic literature. In addition to discussing the main stages of AVM development, we examine empirically the statistical model development and validation step. We find that automated outlier removal is important and that a log model performs best, but only if it accounts for the retransformation problem and heteroscedasticity.

    AB - Market value predictions for residential properties are important for investment decisions and the risk management of households, banks and real estate developers. The increased access to market data has spurred the development and application of Automated Valuation Models (AVMs), which can provide appraisals at low cost. We discuss the stages involved when developing an AVM. By reflecting on our experience with md*immo, an AVM from Berlin, Germany, our paper contributes to an area that has not received much attention in the academic literature. In addition to discussing the main stages of AVM development, we examine empirically the statistical model development and validation step. We find that automated outlier removal is important and that a log model performs best, but only if it accounts for the retransformation problem and heteroscedasticity.

    KW - hedonic regression

    KW - log transformation

    KW - predictive performance

    U2 - 10.1080/09599916.2013.846930

    DO - 10.1080/09599916.2013.846930

    M3 - Article

    VL - 31

    SP - 131

    EP - 153

    JO - Journal of Property Research

    JF - Journal of Property Research

    SN - 0959-9916

    IS - 2

    ER -