izpis_h1_title_alt

Estimating the performance of random forest versus multiple regression for predicting prices of the apartments
ID Čeh, Marjan (Avtor), ID Kilibarda, Milan (Avtor), ID Lisec, Anka (Avtor), ID Bajat, Branislav (Avtor)

.pdfPDF - Predstavitvena datoteka, prenos (3,17 MB)
MD5: 8644ACDA66D6133A3D28B582A7131500
URLURL - Izvorni URL, za dostop obiščite http://www.mdpi.com/2220-9964/7/5/168 Povezava se odpre v novem oknu

Izvleček
The goal of this study is to analyse the predictive performance of the random forest machine learning technique in comparison to commonly used hedonic models based on multiple regression for the prediction of apartment prices. A data set that includes 7407 records of apartment transactions referring to real estate sales from 2008-2013 in the city of Ljubljana, the capital of Slovenia, was used in order to test and compare the predictive performances of both models. Apparent challenges faced during modelling included (1) the non-linear nature of the prediction assignment task; (2) input data being based on transactions occurring over a period of great price changes in Ljubljana whereby a 28% decline was noted in six consecutive testing years; and (3) the complex urban form of the case study area. Available explanatory variables, organised as a Geographic Information Systems (GIS) ready dataset, including the structural and age characteristics of the apartments as well as environmental and neighbourhood information were considered in the modelling procedure. All performance measures (R$^2$ values, sales ratios, mean average percentage error (MAPE), coefficient of dispersion (COD)) revealed significantly better results for predictions obtained by the random forest method, which confirms the prospective of this machine learning technique on apartment price prediction.

Jezik:Angleški jezik
Ključne besede:random forest, OLS, hedonic price model, PCA, Ljubljana
Vrsta gradiva:Članek v reviji
Tipologija:1.01 - Izvirni znanstveni članek
Organizacija:FGG - Fakulteta za gradbeništvo in geodezijo
Status publikacije:Objavljeno
Različica publikacije:Objavljena publikacija
Leto izida:2018
Št. strani:16 str.
Številčenje:Vol. 7, iss. 5, art. 168
PID:20.500.12556/RUL-114444 Povezava se odpre v novem oknu
UDK:004.8:332.85(497.451.1)(049.5)
ISSN pri članku:2220-9964
DOI:10.3390/ijgi7050168 Povezava se odpre v novem oknu
COBISS.SI-ID:8417121 Povezava se odpre v novem oknu
Datum objave v RUL:28.02.2020
Število ogledov:985
Število prenosov:465
Metapodatki:XML RDF-CHPDL DC-XML DC-RDF
:
Kopiraj citat
Objavi na:Bookmark and Share

Gradivo je del revije

Naslov:ISPRS international journal of geo-information
Skrajšan naslov:ISPRS int. j. geo-inf.
Založnik:MDPI
ISSN:2220-9964
COBISS.SI-ID:18678550 Povezava se odpre v novem oknu

Licence

Licenca:CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
Povezava:http://creativecommons.org/licenses/by/4.0/deed.sl
Opis:To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.
Začetek licenciranja:02.05.2018

Sekundarni jezik

Jezik:Slovenski jezik
Ključne besede:strojna metoda učenja, naključni gozd, metoda najmanjših kvadratov, hedonski cenovni model, analiza glavnih komponent, stanovanja, trg nepremičnin, Ljubljana

Projekti

Financer:Drugi - Drug financer ali več financerjev
Številka projekta:451-03-3095/2014-09/34

Podobna dela

Podobna dela v RUL:
Podobna dela v drugih slovenskih zbirkah:

Nazaj