Abstract
This study strives to examine whether consideration of floorplan images of real-estate apartments could be effective for improving rental price predictions. We use a well-established computer vision technique to predict the rental price of apartments exclusively using their floorplan. Afterward, we use these predictions in a traditional hedonic pricing method to see whether its predictions improved. We found that by including floorplans, we were able to increase the accuracy of the out-of-sample predictions from an \(R^{2}\) of 0.914 to an \(R^{2}\) of 0.923. This suggests that floorplans contain considerable information about rent prices, not captured in the other explanatory variables used. Further investigation, including more explanatory variables about the apartment itself, could be used in future research to further examine the price structure of real estate and better understand consumer behavior.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Akiyama, Y.: A study for the mechanism of house rent formation using micro geo-data. Unexpected relationship between living environment and market value of housing. Soc. Environ. Sci. Jpn. 32(2), 53–64 (2019). https://doi.org/10.11353/sesj.32.53
Choi, J.M., Asami, Y.: A study on the hidden structure of residents’ segmentation and evaluation structure on residential satisfaction; the case of UDC rental housing residents in Japan. Urban Housing Sci. 42, 86–97 (2003). https://doi.org/10.11531/uhs1993.2003.42_86. https://cir.nii.ac.jp/crid/1390001205257564032. ISSN 1341-8157
Deng, J., et al.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255 (2009). https://doi.org/10.1109/CVPR.2009.5206848
Fujisawa, M., Inui, T., Hiromatsu, T.: Examination of imputed rent estimation method for considering the quality of housing in subregions: a case study using data from the housing and land survey. Hitotsubashi Univ. Discussion Pap. 20(013), 1–11 (2021)
Hattori, R., Okamoto, K., Shibata, A.: Evaluation of rent prediction models using floor plan images. In: Proceedings of the Annual Conference of JSAI JSAI2019 (2019). https://doi.org/10.11517/pjsai.JSAI2019.0_1D2OS10a05
Hattori, R., Okamoto, K., Shibata, A.: Rent prediction models with floor plan images. In: 2019 IEEE 8th Global Conference on Consumer Electronics (GCCE), pp. 451–452 (2019). https://doi.org/10.1109/GCCE46687.2019.9015208
He, K., et al.: Deep residual learning for image recognition (2015). arXiv:1512.03385v1
Howard, J., Gugger, S.: FastAI: a layered API for deep learning. CoRR (2020). arXiv:2002.04688 [cs.LG]
Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017). arXiv:1412.6980 [cs.LG]
Krainer, J., Wei, C.: House prices and fundamental value. In: FRBSF Economic Letter (2004)
Limsombunchai, V., Gan, C., Lee, M.: House price prediction: hedonic price model vs. artificial neural network. Am. J. Appl. Sci. 1 (2004). https://doi.org/10.3844/ajassp.2004.193.201
Lundberg, S.M., Lee, S.-I.: A unified approach to interpreting model predictions. In: Guyon, I., et al. (eds.) Advances in Neural Information Processing Systems, vol. 30, pp. 4765–4774. Curran Associates Inc. (2017)
Moriizumi, Y.: Estimation of housing price index and demand price elasticity for urban housing in Japan. J. Jpn. Stat. Soc. 16(1), 81–100 (1986)
Nelson, J.P.: Residential choice, hedonic prices, and the demand for urban air quality. J. Urban Econ. 5(3), 357–369 (1978). https://doi.org/10.1016/0094-1190(78)90016-5. https://www.sciencedirect.com/science/article/pii/0094119078900165. ISSN 0094-1190
Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Wallach, H., et al. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 8024–8035. Curran Associates Inc. (2019)
Poursaeed, O., Matera, T., Belongie, S.: Vision-based real estate price estimation. Mach. Vis. Appl. 29(4), 667–676 (2018). https://doi.org/10.1007/s00138-018-0922-2
Rosen, S.: Hedonic prices and implicit markets: product differentiation in pure competition. J. Polit. Econ. 82(1), 34–55 (1974). http://www.jstor.org/stable/1830899. ISSN 00223808, 1537534X
Smith, L.N.: Cyclical learning rates for training neural networks (2017). arXiv:1506.01186 [cs.CV]
Solovev, K., Prollochs, N.: Integrating floor plans into hedonic models for rent price appraisal. In: Proceedings of the Web Conference 2021, WWW 2021, Ljubljana, Slovenia, pp. 2838–2847. Association for Computing Machinery (2021). https://doi.org/10.1145/3442381.3449967. ISBN 9781450383127
Urban Developers’ Association of Japan. Divergence between the price of medium-high rise buildings and the household income of office workers: Survey result announcement of the three big cities for the year Heisei 10. Urban Developers’ Association of Japan (1999)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
A Appendix
A Appendix
This figure showcases the properties of each resizing method. The first and second rows compare nine floorplans. The third shows different crops of the leftmost floorplan.
(Taken from test dataset)
This figure shows some of the NN’s minimal and maximal predictions (in \(10,000\)¥).
(Taken from test dataset)
This figure shows floorplans of the predictions where an inclusion of the NN’s predictions introduced the largest changes (in \(10,000\)¥).
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Schneider, J.J., Hoshino, T. (2023). Incremental Informational Value of Floorplans for Rent Price Prediction. In: Takama, Y., Yada, K., Satoh, K., Arai, S. (eds) New Frontiers in Artificial Intelligence. JSAI-isAI 2022. Lecture Notes in Computer Science(), vol 13859. Springer, Cham. https://doi.org/10.1007/978-3-031-29168-5_16
Download citation
DOI: https://doi.org/10.1007/978-3-031-29168-5_16
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-29167-8
Online ISBN: 978-3-031-29168-5
eBook Packages: Computer ScienceComputer Science (R0)