Vision-based real estate price estimation

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Vision-based real estate price estimation. / Poursaeed, Omid; Matera, Tomáš; Belongie, Serge.

I: Machine Vision and Applications, Bind 29, Nr. 4, 01.05.2018, s. 667-676.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Poursaeed, O, Matera, T & Belongie, S 2018, 'Vision-based real estate price estimation', Machine Vision and Applications, bind 29, nr. 4, s. 667-676. https://doi.org/10.1007/s00138-018-0922-2

APA

Poursaeed, O., Matera, T., & Belongie, S. (2018). Vision-based real estate price estimation. Machine Vision and Applications, 29(4), 667-676. https://doi.org/10.1007/s00138-018-0922-2

Vancouver

Poursaeed O, Matera T, Belongie S. Vision-based real estate price estimation. Machine Vision and Applications. 2018 maj 1;29(4):667-676. https://doi.org/10.1007/s00138-018-0922-2

Author

Poursaeed, Omid ; Matera, Tomáš ; Belongie, Serge. / Vision-based real estate price estimation. I: Machine Vision and Applications. 2018 ; Bind 29, Nr. 4. s. 667-676.

Bibtex

@article{9655253787c64d398d66ec7c23309abb,
title = "Vision-based real estate price estimation",
abstract = "Since the advent of online real estate database companies like Zillow, Trulia and Redfin, the problem of automatic estimation of market values for houses has received considerable attention. Several real estate websites provide such estimates using a proprietary formula. Although these estimates are often close to the actual sale prices, in some cases they are highly inaccurate. One of the key factors that affects the value of a house is its interior and exterior appearance, which is not considered in calculating automatic value estimates. In this paper, we evaluate the impact of visual characteristics of a house on its market value. Using deep convolutional neural networks on a large dataset of photos of home interiors and exteriors, we develop a method for estimating the luxury level of real estate photos. We also develop a novel framework for automated value assessment using the above photos in addition to home characteristics including size, offered price and number of bedrooms. Finally, by applying our proposed method for price estimation to a new dataset of real estate photos and metadata, we show that it outperforms Zillow{\textquoteright}s estimates.",
keywords = "Automated valuation method, Computer vision, Convolutional neural networks, Crowdsourcing, Real estate",
author = "Omid Poursaeed and Tom{\'a}{\v s} Matera and Serge Belongie",
note = "Publisher Copyright: {\textcopyright} 2018, Springer-Verlag GmbH Germany, part of Springer Nature.",
year = "2018",
month = may,
day = "1",
doi = "10.1007/s00138-018-0922-2",
language = "English",
volume = "29",
pages = "667--676",
journal = "Machine Vision and Applications",
issn = "0932-8092",
publisher = "Springer",
number = "4",

}

RIS

TY - JOUR

T1 - Vision-based real estate price estimation

AU - Poursaeed, Omid

AU - Matera, Tomáš

AU - Belongie, Serge

N1 - Publisher Copyright: © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Since the advent of online real estate database companies like Zillow, Trulia and Redfin, the problem of automatic estimation of market values for houses has received considerable attention. Several real estate websites provide such estimates using a proprietary formula. Although these estimates are often close to the actual sale prices, in some cases they are highly inaccurate. One of the key factors that affects the value of a house is its interior and exterior appearance, which is not considered in calculating automatic value estimates. In this paper, we evaluate the impact of visual characteristics of a house on its market value. Using deep convolutional neural networks on a large dataset of photos of home interiors and exteriors, we develop a method for estimating the luxury level of real estate photos. We also develop a novel framework for automated value assessment using the above photos in addition to home characteristics including size, offered price and number of bedrooms. Finally, by applying our proposed method for price estimation to a new dataset of real estate photos and metadata, we show that it outperforms Zillow’s estimates.

AB - Since the advent of online real estate database companies like Zillow, Trulia and Redfin, the problem of automatic estimation of market values for houses has received considerable attention. Several real estate websites provide such estimates using a proprietary formula. Although these estimates are often close to the actual sale prices, in some cases they are highly inaccurate. One of the key factors that affects the value of a house is its interior and exterior appearance, which is not considered in calculating automatic value estimates. In this paper, we evaluate the impact of visual characteristics of a house on its market value. Using deep convolutional neural networks on a large dataset of photos of home interiors and exteriors, we develop a method for estimating the luxury level of real estate photos. We also develop a novel framework for automated value assessment using the above photos in addition to home characteristics including size, offered price and number of bedrooms. Finally, by applying our proposed method for price estimation to a new dataset of real estate photos and metadata, we show that it outperforms Zillow’s estimates.

KW - Automated valuation method

KW - Computer vision

KW - Convolutional neural networks

KW - Crowdsourcing

KW - Real estate

UR - http://www.scopus.com/inward/record.url?scp=85044739259&partnerID=8YFLogxK

U2 - 10.1007/s00138-018-0922-2

DO - 10.1007/s00138-018-0922-2

M3 - Journal article

AN - SCOPUS:85044739259

VL - 29

SP - 667

EP - 676

JO - Machine Vision and Applications

JF - Machine Vision and Applications

SN - 0932-8092

IS - 4

ER -

ID: 301826358