Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Using photographs and metadata to estimate house prices in South Korea

Using photographs and metadata to estimate house prices in South Korea Most prior attempts at real estate valuation have focused on the use of metadata such as size and property age, neglecting the fact that the building workmanship in the construction of a house is also a key factor for the estimation of house prices. Building workmanship, such as exterior walls and floor tiling correspond to the visual attributes of a house, and it is difficult to capture and evaluate such attributes efficiently through classical models like regression analysis. Deep learning approach is taken in the valuation process to utilize this visual information.Design/methodology/approachThe authors propose a two-input neural network comprising a multilayer perceptron and a convolutional neural network that can utilize both metadata and the visual information from images of the front view of the house.FindingsThe authors applied the two-input neural network to Guri City in Gyeonggi Province, South Korea, as a case study and found that the accuracy of house price estimations can be improved by employing image information along with metadata.Originality/valueFew studies considered the impact of the building workmanship in the valuation process. The authors revealed that it is useful to use both photographs and metadata for enhancing the accuracy of house price estimation. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Data Technologies and Applications Emerald Publishing

Using photographs and metadata to estimate house prices in South Korea

Lee, Changro; Park, Key-Ho
Data Technologies and Applications , Volume 55 (2): 13 – Apr 12, 2021
Download PDF
13 pages

Loading next page...
 
/lp/emerald-publishing/using-photographs-and-metadata-to-estimate-house-prices-in-south-korea-rcL0LQfyev
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
2514-9288
DOI
10.1108/dta-05-2020-0111
Publisher site
See Article on Publisher Site

Abstract

Most prior attempts at real estate valuation have focused on the use of metadata such as size and property age, neglecting the fact that the building workmanship in the construction of a house is also a key factor for the estimation of house prices. Building workmanship, such as exterior walls and floor tiling correspond to the visual attributes of a house, and it is difficult to capture and evaluate such attributes efficiently through classical models like regression analysis. Deep learning approach is taken in the valuation process to utilize this visual information.Design/methodology/approachThe authors propose a two-input neural network comprising a multilayer perceptron and a convolutional neural network that can utilize both metadata and the visual information from images of the front view of the house.FindingsThe authors applied the two-input neural network to Guri City in Gyeonggi Province, South Korea, as a case study and found that the accuracy of house price estimations can be improved by employing image information along with metadata.Originality/valueFew studies considered the impact of the building workmanship in the valuation process. The authors revealed that it is useful to use both photographs and metadata for enhancing the accuracy of house price estimation.

Journal

Data Technologies and Applications – Emerald Publishing

Published: Apr 12, 2021

Keywords: Metadata; Image; Deep learning; Two-input neural network; House prices; Valuation

References

  • Artificial neural network in property valuation: application framework and research trend
    Abidoye, R.B.; Chan, A.P.
  • A review of real estate valuation and optimal pricing techniques
    Adetiloye, K.A.; Eke, P.O.
  • House price estimation from visual and textual features
    Ahmed, E.; Moustafa, M.
  • Mass appraisal: an introduction to multiple regression analysis for real estate valuation
    Benjamin, J.; Guttery, R.; Sirmans, C.F.
  • A critical review of literature on the hedonic price model
    Chau, K.W.; Chin, T.L.
  • Prediction of housing location price by a multivariate spatial method: cokriging
    Chica-Olmo, J.
  • Determinants of house price: a decision tree approach
    Fan, G.Z.; Ong, S.E.; Koh, H.C.
  • Comparison of bagging, boosting and stacking ensembles applied to real estate appraisal
    Graczyk, M.; Lasota, T.; Trawiński, B.; Trawiński, K.
  • Simple convolutional neural network on image classification
    Guo, T.; Dong, J.; Li, H.; Gao, Y.
  • Deep residual learning for image recognition
    He, K.; Zhang, X.; Ren, S.; Sun, J.
  • Location, location, location: the 3L Approach to house price determination
    Kiel, K.A.; Zabel, J.E.
  • Support vector machine and entropy based decision support system for property valuation
    Lam, K.C.; Yu, C.Y.; Lam, C.K.
  • Investigation of random subspace and random forest methods applied to property valuation data
    Lasota, T.; Łuczak, T.; Trawiński, B.
  • Take a look around: using street view and satellite images to estimate house prices
    Law, S.; Paige, B.; Russell, C.
  • High‐tech valuation: should artificial neural networks bypass the human valuer?
    Lenk, M.M.; Worzala, E.M.; Silva, A.
  • Research on mass real estate evaluation mode based on BP neural network model
    Ma, K.; Zhang, Y.; Yang, Z.
  • The potential of artificial neural networks in mass appraisal: the case revisited
    McCluskey, W.; Davis, P.; Haran, M.; McCord, M.; McIlhatton, D.
  • Neural networks: the prediction of residential values
    McGreal, S.; Adair, A.; McBurney, D.; Patterson, D.
  • Changes in the distribution of house prices over time: structural characteristics, neighborhood, or coefficients?
    McMillen, D.P.
  • Discrimination and neighborhood effects: understanding racial differentials in US housing prices
    Myers, C.K.
  • An introduction to convolutional neural networks
    O’Shea, K.; Nash, R.
  • An application of spatial econometrics in relation to hedonic house price modeling
    Osland, L.
  • Effects on housing prices of urban attraction and labor-market accessibility
    Osland, L.; Thorsen, I.
  • Real estate appraisal: a review of valuation methods
    Pagourtzi, E.; Assimakopoulos, V.; Hatzichristos, T.; French, N.
  • A new deep convolutional neural network for fast hyperspectral image classification
    Paoletti, M.E.; Haut, J.M.; Plaza, J.; Plaza, A.
  • Deep learning for detecting building defects using convolutional neural networks
    Perez, H.; Tah, J.H.; Mosavi, A.
  • Vision-based real estate price estimation
    Poursaeed, O.; Matera, T.; Belongie, S.
  • Fusionnet: a deep fully residual convolutional neural network for image segmentation in connectomics
    Quan, T.M.; Hildebrand, D.G.; Jeong, W.K.
  • Impact of outlier detection on neural networks based property value prediction
    Sandbhor, S.; Chaphalkar, N.B.
  • Determinants of house prices in Turkey: a hedonic regression model
    Selim, S.
  • Apartment valuation models for a big city using selected spatial attributes
    Talaga, M.; Piwowarczyk, M.; Kutrzyński, M.; Lasota, T.; Telec, Z.; Trawiński, B.
  • Crime and residential choice: a neighborhood level analysis of the impact of crime on housing prices
    Tita, G.E.; Petras, T.L.; Greenbaum, R.T.
  • Residential housing prices: impact of housing characteristics, accessibility and neighbouring apartments–a case study of Dortmund, Germany
    Wittowsky, D.; Hoekveld, J.; Welsch, J.; Steier, M.
  • Area-to-point Kriging in spatial hedonic pricing models
    Yoo, E.H.; Kyriakidis, P.C.
  • Determinants of house prices: a quantile regression approach
    Zietz, J.; Zietz, E.N.; Sirmans, G.S.