Journal of the Economic Geographical Society of Korea (한국경제지리학회지)

The Economic Geographical Society of Korea (한국경제지리학회)
권호 표지
DOI QR코드

DOI QR Code

How the Pattern Recognition Ability of Deep Learning Enhances Housing Price Estimation

딥러닝의 패턴 인식능력을 활용한 주택가격 추정

  • Kim, Jinseok (Department of Environmental Planning, Graduate School of Environmental Studies, Seoul National University) ;
  • Kim, Kyung-Min (Department of Environmental Planning, Graduate School of Environmental Studies, Seoul National University)
  • 김진석 (서울대학교 환경대학원) ;
  • 김경민 (서울대학교 환경대학원)
  • Received : 2022.02.24
  • Accepted : 2022.03.15
  • Published : 2022.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

Estimating the implicit value of housing assets is a very important task for participants in the housing market. Until now, such estimations were usually carried out using multiple regression analysis based on the inherent characteristics of the estate. However, in this paper, we examine the estimation capabilities of the Artificial Neural Network(ANN) and its 'Deep Learning' faculty. To make use of the strength of the neural network model, which allows the recognition of patterns in data by modeling non-linear and complex relationships between variables, this study utilizes geographic coordinates (i.e. longitudinal/latitudinal points) as the locational factor of housing prices. Specifically, we built a dataset including structural and spatiotemporal factors based on the hedonic price model and compared the estimation performance of the models with and without geographic coordinate variables. The results show that high estimation performance can be achieved in ANN by explaining the spatial effect on housing prices through the geographic location.

주택가격을 정확히 추정하기 위한 많은 연구가 진행되어 왔다. 선행연구들은 주택의 고유 특성과 인근 지역 특성을 통제하는 계량경제모형을 활용한 분석이 많았다. 본 연구에서는 인공신경망 모형(ANN)을 활용하여 주택가격을 추정하였다. 딥러닝 기술의 장점은 변수 간의 복잡하고 비선형적인 특성을 모델링하고 데이터의 패턴을 인식할 수 있다는 것이다. 본 연구에서는 부동산 시장에서 공간적 분포도 패턴으로 인식할 수 있다는 가정하에 지리좌표를 설명변수로 ANN에 투입하였다. 선형회귀분석과 ANN 모형 간 비교 결과, 선형 모형 대비 ANN 모형의 설명력이 높았으며, 특히 ANN 모형은 지리좌표를 투입하였을 때 더 높은 정확도를 보여주었다. 또한 ANN 모형의 경우 지리좌표를 통해 모형 잔차의 공간적 자기 상관성이 크게 감소하였다는 점을 확인하였다. 이를 통해 ANN 모형의 패턴인식 능력을 활용하면 공간적 패턴을 학습시킴으로써 주택가격을 정확히 추정할 수 있음을 밝혔다.

Keywords

Acknowledgement

This work was supported by SNU Environmental Planning Institute.

References

  1. Abidoye, R. B., and Chan, A. P., 2018, "Improving property valuation accuracy: A comparison of hedonic pricing model and artificial neural network," Pacific Rim Property Research Journal 24(1), pp.71-83. https://doi.org/10.1080/14445921.2018.1436306
  2. Anselin, L., 1998, "GIS research infrastructure for spatial analysis of real estate markets," Journal of Housing Research 9(1), pp.113-133. https://doi.org/10.1080/10835547.1998.12091930
  3. Basu, S., and Thibodeau, T. G., 1998, "Analysis of spatial autocorrelation in house prices," The Journal of Real Estate Finance and Economics 17(1), pp.61-85. https://doi.org/10.1023/A:1007703229507
  4. Can, A., 1992, "Specification and estimation of hedonic housing price models," Regional science and urban economics 22(3), pp.453-474. https://doi.org/10.1016/0166-0462(92)90039-4
  5. Case, B., Clapp, J., Dubin, R., and Rodriguez, M., 2004, "Modeling spatial and temporal house price patterns: A comparison of four models," The Journal of Real Estate Finance and Economics 29(2), pp.167-191. https://doi.org/10.1023/B:REAL.0000035309.60607.53
  6. Chollet, F., 2017, Deep learning with Python, Manning Publications Company.
  7. Chun, H. J., 2012, "Liquidity-related Variables Impact on Housing Prices and Policy Implications," Journal of the Economic Geographical Society of Korea 15(4), pp.585-600. (Korean) https://doi.org/10.23841/egsk.2012.15.4.585
  8. Do, Q., and Grudnitski, G., 1993, "A neural network analysis of the effect of age on housing values," Journal of Real Estate Research 8(2), pp.253-264. https://doi.org/10.1080/10835547.1993.12090712
  9. Dodgson, J. S., and Topham, N., 1990, "Valuing residential properties with the hedonic method: A comparison with the results of professional valuations," Housing Studies 5(3), pp.209-213. https://doi.org/10.1080/02673039008720685
  10. Dubin, R. A., 1992, "Spatial autocorrelation and neighborhood quality," Regional science and urban economics 22(3), pp.433-452. https://doi.org/10.1016/0166-0462(92)90038-3
  11. Edmonds Jr, R. G., 1984, "A theoretical basis for hedonic regression: A research primer," Real Estate Economics 12(1), pp.72-85. https://doi.org/10.1111/1540-6229.00311
  12. Fotheringham, A. S., Charlton, M. E., and Brunsdon, C., 1998, "Geographically weighted regression: a natural evolution of the expansion method for spatial data analysis," Environment and planning A 30(11), pp.1905-1927. https://doi.org/10.1068/a301905
  13. Garcia, N., Gamez, M., and Alfaro, E., 2008, "ANN+GIS: An automated system for property valuation," Neurocomputing 71(4-6), pp.733-742. https://doi.org/10.1016/j.neucom.2007.07.031
  14. Geron, A., 2017, Hands-On Machine Learning with Scikit-Learn and TensorFlow, O'Reilly Media.
  15. Ghorbani, S., and Afgheh, S. M., 2017, "Forecasting the house price for ahvaz city: the comparison of the hedonic and artificial neural network models," Journal of Urban Economics and Management 5(19), pp.29-44.
  16. Goodman, A. C., 1978, "Hedonic prices, price indices and housing markets," Journal of urban economics 5(4), pp.471-484. https://doi.org/10.1016/0094-1190(78)90004-9
  17. Goodman, A. C., and Thibodeau T. G., 1998, "Housing market segmentation," Journal of housing economics 7(2), pp.121-143. https://doi.org/10.1006/jhec.1998.0229
  18. Haykin, S., 2003, Neural Networks: A Comprehensive Foundation 2nd Edition, Prentice Hall PTR.
  19. Herath, S. K., and Maier, G., 2011, "Hedonic house prices in the presence of spatial and temporal dynamics," Territorio Italia land Administration, Cadastre, Real Estate 1(1), pp.39-49.
  20. Huang, B., Wu, B., and Barry, M., 2010, "Geographically and temporally weighted regression for modeling spatio-temporal variation in house prices," International Journal of Geographical Information Science 24(3), pp.383-401. https://doi.org/10.1080/13658810802672469
  21. Jeong, J. H., 2014, "An Analysis of Network Structure in Housing Markets: the Case of Apartment Sales Markets in the Capital Region," Journal of the Economic Geographical Society of Korea 17(2), pp.280-295. (Korean) https://doi.org/10.23841/EGSK.2014.17.2.280
  22. Khalafallah, A., 2008, "Neural network based model for predicting housing market performance," Tsinghua Science and Technology 13(S1), pp.325-328. https://doi.org/10.1016/S1007-0214(08)70169-X
  23. Kim, S. J., Jeong, J. H., and Seo, K. C., 2015, "The Conversion Trend of Jeonsei to Monthly Rent Contracts and Its Major Characteristics: The Case of Three Gangnam Districts' APT Rental Market in Seoul," Journal of the Economic Geographical Society of Korea 18(3), pp.348-365. (Korean) https://doi.org/10.23841/egsk.2015.18.3.348
  24. Koki, S., 2016, Deep Learning from Scratch, OREILLY JAPAN.
  25. Law, S., Paige, B., and Russell, C., 2019, "Take a look around: using street view and satellite images to estimate house prices," ACM Transactions on Intelligent Systems and Technology 10(5), pp.1-19.
  26. Law, S., Seresinhe, C. I., Shen, Y., and Gutierrez-Roig, M., 2020, "Street-Frontage-Net: urban image classification using deep convolutional neural networks," International Journal of Geographical Information Science 34(4), pp.681-707. https://doi.org/10.1080/13658816.2018.1555832
  27. LeCun, Y., Bengio, Y., and Hinton, G., 2015, "Deep learning," nature 521(7553), pp.436-444. https://doi.org/10.1038/nature14539
  28. Lee, C., and S. H. Kim, 2018, "The Deep Learning Approach to Property Valuation: An Application of a Multilayer Neural Net Model for Estimating House Prices," Journal of The Korean Regional Development Association 30(4), pp.179-201. https://doi.org/10.22885/KRDA.2018.30.4.179
  29. Lee, W. D., Won, J. S., and Joh, C. S., 2011, "A Study of Correlation between Air Environment Index and Urban Spatial Structure: Based On Land Use and Traffic Data In Seoul," Journal of the Economic Geographical Society of Korea 14(2), pp.143-156. (Korean) https://doi.org/10.23841/egsk.2011.14.2.143
  30. Lenk, M. M., Worzala, E. M., and Silva, A., 1997, "Hightech valuation: should artificial neural networks bypass the human valuer?" Journal of Property Valuation and Investment 15(1), pp.8-26. https://doi.org/10.1108/14635789710163775
  31. Loo, W. K., 2019, "Predictability of HK-REITs returns using artificial neural network," Journal of Property Investment & Finance 38(4), pp.291-307. https://doi.org/10.1108/JPIF-07-2019-0090
  32. Lu, B., Charlton, M., Harris, P., and Fotheringham, A. S., 2014, "Geographically weighted regression with a non-Euclidean distance metric: a case study using hedonic house price data," International Journal of Geographical Information Science 28(4), pp.660-681. https://doi.org/10.1080/13658816.2013.865739
  33. Mimis, A., Rovolis, A., and Stamou, M., 2013, "Property valuation with artificial neural network: the case of Athens," Journal of Property Research 30(2), pp.128-143. https://doi.org/10.1080/09599916.2012.755558
  34. Osland, L., 2010, "An application of spatial econometrics in relation to hedonic house price modeling," Journal of Real Estate Research 32(3), pp.289-320. https://doi.org/10.1080/10835547.2010.12091282
  35. Pai, P. F., and Wang, W. C., 2020, "Using machine learning models and actual transaction data for predicting real estate prices," Applied Sciences 10(17), pp.5832. https://doi.org/10.3390/app10175832
  36. Peterson, S., and Flanagan, A., 2009, "Neural network hedonic pricing models in mass real estate appraisal," Journal of Real Estate Research 31(2), pp.147-164. https://doi.org/10.1080/10835547.2009.12091245
  37. Poursaeed, O., Matera, T., and Belongie, S., 2018, "Vision-based real estate price estimation," Machine Vision and Applications 29(4), pp.667-676. https://doi.org/10.1007/s00138-018-0922-2
  38. Raschka, S., and Mirjalili, V., 2019, Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2, Packt Publishing Ltd.
  39. Rosen, S., 1974, "Hedonic prices and implicit markets: product differentiation in pure competition," Journal of political economy 82(1), pp.34-55. https://doi.org/10.1086/260169
  40. Stamou, M., Mimis, A., and Rovolis, A., 2017, "House price determinants in Athens: a spatial econometric approach," Journal of Property Research 34(4), pp.269-284. https://doi.org/10.1080/09599916.2017.1400575
  41. Tay, D. P., and Ho, D. K., 1992, "Artificial intelligence and the mass appraisal of residential apartments," Journal of Property Valuation and Investment 10(2), pp.525-540. https://doi.org/10.1108/14635789210031181
  42. Tobler, W. R., 1970, "A computer movie simulating urban growth in the Detroit region," Economic geography 46, pp.234-240. https://doi.org/10.2307/143141
  43. Worzala, E., Lenk, M., and Silva, A., 1995, "An exploration of neural networks and its application to real estate valuation," Journal of Real Estate Research 10(2), pp.185-201. https://doi.org/10.1080/10835547.1995.12090782
  44. Yang, J. S., 2017, "The Spillover Effect of Public Hosing Policy on Rental Housing Market: The Case of Seoul, Korea," Journal of the Economic Geographical Society of Korea 20(3), pp.403-416. (Korean) https://doi.org/10.23841/EGSK.2017.20.3.403
  45. Zhou, X., Tong, W., and Li, D., 2019, "Modeling Housing Rent in the Atlanta Metropolitan Area Using Textual Information and Deep Learning," ISPRS International Journal of Geo-Information 8(8), pp.349. https://doi.org/10.3390/ijgi8080349
  46. Zietz, J., Zietz, E. N., and Sirmans, G. S., 2008, "Determinants of house prices: a quantile regression approach," The Journal of Real Estate Finance and Economics 37(4), pp.317-333. https://doi.org/10.1007/s11146-007-9053-7