Application of the J48 Decision Tree Algorithm in the Mass Valuation of Real Estate

Autor:	Nelson Obregon, Edwin Robert Perez, Adriana Albancando
Rok vydání:	2020
Předmět:	Valuation (logic) C4.5 algorithm Computer science Decision tree learning Econometrics Real estate
DOI:	10.21203/rs.2.23397/v1
Popis:	This article presents the results of the research work of the GIGA research group of the Distrital University in Bogota Colombia in the framework of the advanced doctoral research in the engineering doctorate of the Javeriana University and shows the development followed and the corresponding analysis determine the effectiveness of the M5P algorithm within the decision tree approach for the management of BIG DATA and Machine Learning for the determination of massive property valuation. The analysis was carried out with data provided by the Special Administrative Unit of the Distrital Cadaster (UAECD) and the Technical Cadastral Observatory corresponding to three sectors of the city of Bogotá D.C. The results of the J48-based model were compared by means of a statistical analysis with the traditionally used linear regression method, obtaining satisfactory results with errors well below the linear regressions in the training, validation and forecast stages.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::b43e8000603d7dbeb219fb9c44cbc292 https://doi.org/10.21203/rs.2.23397/v1 Zobrazit plný text záznamu