TESTING THE GENERALIZATION OF AUTOMATED REAL ESTATE PROPERTY EVALUATION MODELS

Eric Tzimas () and Manolis Kritikos ()
Additional contact information
Eric Tzimas: Hobsido, Athens
Manolis Kritikos: Athens University of Economics and Business

Journal of Information Systems & Operations Management, 2022, vol. 16, issue 2, 273-282

Abstract: The goal of this paper is to analyze the implementation of an automation valuation model in real estate and provide insight regarding its behavior when faced with real world data. An automated valuation model was implemented using two different datasets from Ames Iowa and Athens Greece. The models implemented were a KNeighborsRegressor, a GradientBoostingRegressor, a DecisionTreeRegressor, a Random Forest Regressor, a Stacked Regressor, and a Neural Network. The best scoring model for both datasets was the Random Forest Regressor. Two different methods were used for the evaluation of the above models. These methods include testing using twenty percent of the starting dataset and testing using a custom dataset created by authorized property appraisers. In both techniques, the models scored similarly, with only a three percent difference in accuracy, showcasing the rigidity and robustness of the valuation model when faced with external and quality assured data.

Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.rebe.rau.ro/RePEc/rau/jisomg/WI22/JISOM-WI22-A22.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:rau:jisomg:v:16:y:2022:i:2:p:273-282

Access Statistics for this article

More articles in Journal of Information Systems & Operations Management from Romanian-American University Contact information at EDIRC.
Bibliographic data for series maintained by Alex Tabusca ().