+1 Recommend
    • Review: found
    Is Open Access

    Review of 'Property valuation by machine learning for the Norwegian real estate market'

    Property valuation by machine learning for the Norwegian real estate marketCrossref
    It is quite interesting but the originality of this work is very trivial.
    Average rating:
        Rated 3 of 5.
    Level of importance:
        Rated 2 of 5.
    Level of validity:
        Rated 2 of 5.
    Level of completeness:
        Rated 3 of 5.
    Level of comprehensibility:
        Rated 4 of 5.
    Competing interests:

    Reviewed article

    • Record: found
    • Abstract: found
    • Article: found
    Is Open Access

    Property valuation by machine learning for the Norwegian real estate market

    We train a machine learning model on large data set for predicting property values in the Norwegian real estate market. Our model is a gradient boosted regression tree. The data set is the largest market data set of properties in Norway considered in the research literature. We achieve state of the art accuracy. A large scale market data set of real estate properties is collected from sales and rental ads on publicly accessible internet sites. The property advertisements show property features and appraisal values made by real estate brokers. We train a gradient boosted regression tree model on selected features of the data set. This is a multivariate regression model built with supervised learning. We do 5-fold cross validation to assess the accuracy and robustness of the model. The gradient boosted regression tree models are already known to give the best prediction accuracy on real estate price valuations. We achieve state of the art pre- diction accuracy using a minimal feature set and only publicly and freely available sales advertisement data. The novelty of our work lies in the fact that we use a minimal feature set in our model, and we have the largest data set in the research literature, and moreover we have used only freely and publicly accessible data which are simple to obtain. This shows that useful estimation models with high accuracy can be built with quite simple resources.

      Review information

      This work has been published open access under Creative Commons Attribution License CC BY 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. Conditions, terms of use and publishing policy can be found at www.scienceopen.com.

      prediction,property valuation,property price prediction,automated valuation model,artifical intelligence,house price prediction,machine learning,real estate,price

      Review text

      (1) The authors have proposed a Machine Learning model, which is based on Gradient-Boosted Regression, for learning over Norwegian real estate datasets such that predications can be made with regard to the value of real estate properties in Norway.


      (1) The authors have NOT given details with respect to comparative analyses based on other state-of-the-art models/methods applied to resolving problems of this nature.


      (1) The authors have aggregated quite some good sample of original data which will be very relevant to training Machine Learning and Deep Learning models in related tasks.
      (2) Real Estate study is an interesting topic especially with regard to the 21st century and the business/investment world.


      Related Work
      (1) The review of related literature in this research is barely adequate/sufficient.
      (2) The contribution of this paper with regard to Machine Learning (ML) models is not quite significant.


      Discussion and Clarity
      (1) The use of English herein by the authors is quite good and satisfiable. Thus, this made the manuscript quite easy to read and comprehend.


      Concerns/Comments and Weaknesses 
      (1) With respect to the work/experiments carried out by the authors herein; this work seems to be localized to the Norwegian Real Estate system. In this regard, the work herein may not be of widespread importance to the general populace with respect to every continent of the world.
      (2) This claim in Section 1.3 is not always true: "The gradient boosted regression tree models are already known to give the best
      prediction accuracy on real estate price valuations." In this regard, effective accuracy over a dataset with respect to a regression model is dependent on several factors that border on the cleanliness and completeness of the input dataset.
      (3) The originality of this work as presented in Section 1.4 is trivial. Dimensionality reduction with respect to the feature space is a popular and well-known approach toward analyzing and training Machine Learning and Deep Learning models.
      (4) The work presented herein is a popular exercise which is present in most introductory practical Machine Learning and/or Deep Learning textbooks.
      (5) The experimental analyses herein have not been well detailed by the authors. No comparative analyses/results with respect to other benchmark and/or state-of-the-art models in this domain.
      (6) The authors have not given proper details with regard to the architecture and formalism of their proposed framework/model.
      (7) There is no formal definition to the problem(s) the authors have attempted to resolve herein.


      Comment on this review

      Version and Review History