Applying data mining algorithms to real estate appraisals: a comparative study
International Journal of Housing Markets and Analysis
ISSN: 1753-8270
Article publication date: 8 February 2021
Issue publication date: 12 November 2021
Abstract
Purpose
Real estate appraisals are becoming an increasingly important means of backing up financial operations based on the values of these kinds of assets. However, in very large databases, there is a reduction in the predictive capacity when traditional methods, such as multiple linear regression (MLR), are used. This paper aims to determine whether in these cases the application of data mining algorithms can achieve superior statistical results. First, real estate appraisal databases from five towns and cities in the State of Paraná, Brazil, were obtained from Caixa Econômica Federal bank.
Design/methodology/approach
After initial validations, additional databases were generated with both real, transformed and nominal values, in clean and raw data. Each was assisted by the application of a wide range of data mining algorithms (multilayer perceptron, support vector regression, K-star, M5Rules and random forest), either isolated or combined (regression by discretization – logistic, bagging and stacking), with the use of 10-fold cross-validation in Weka software.
Findings
The results showed more varied incremental statistical results with the use of algorithms than those obtained by MLR, especially when combined algorithms were used. The largest increments were obtained in databases with a large amount of data and in those where minor initial data cleaning was carried out. The paper also conducts a further analysis, including an algorithmic ranking based on the number of significant results obtained.
Originality/value
The authors did not find similar studies or research studies conducted in Brazil.
Keywords
Acknowledgements
The authors would like to thank the staff of the CEF Bank for assisting us in undertaking this study. Authors are particularly grateful to Ana Carolina, from the team that selected this research for funding in preference to other projects; Mariana and Helaine, also from the head office of CEF, for accepting the plans of the project and helping to obtain the authorization needed; the managers from the CEF’s State of Paraná branches at the time the macromodels were collected: Viriato, George, Leonardo, Ernesto, Henrique and Itamar, for providing the materials for this study. They thanks too to all the colleagues that either directly or at some level gave assistance to this work. We would also like to thank the “Institutos Lactec,” especially Professors Ana Paula and Débora and Prof Milton (invited professor), for making valuable observations during the master’s defense assessment that subsequently helped shape this article. Our thanks too to the developers of the Weka software, from the University of Waikato, in New Zealand, especially Prof Ian H. Witten. The discovery of Weka was a major factor in our research. Finally, the authors would also like to thank in advance the anonymous reviewer from the journal for devoting both time and effort to assessing this article.
Citation
Oliveira, T.C.d., Medeiros, L.d. and Detzel, D.H.M. (2021), "Applying data mining algorithms to real estate appraisals: a comparative study", International Journal of Housing Markets and Analysis, Vol. 14 No. 5, pp. 969-986. https://doi.org/10.1108/IJHMA-07-2020-0080
Publisher
:Emerald Publishing Limited
Copyright © 2021, Emerald Publishing Limited