DOI QR코드

DOI QR Code

Prediction and factors of Seoul apartment price using convolutional neural networks

CNN 모형을 이용한 서울 아파트 가격 예측과 그 요인

  • Lee, Hyunjae (Department of Statistics, Sungkyunkwan University) ;
  • Son, Donghui (Department of Statistics, Sungkyunkwan University) ;
  • Kim, Sujin (Department of Statistics, Sungkyunkwan University) ;
  • Oh, Sein (Department of Sports Science, Sungkyunkwan University) ;
  • Kim, Jaejik (Department of Statistics, Sungkyunkwan University)
  • 이현재 (성균관대학교 통계학과) ;
  • 손동희 (성균관대학교 통계학과) ;
  • 김수진 (성균관대학교 통계학과) ;
  • 오세인 (성균관대학교 스포츠과학과) ;
  • 김재직 (성균관대학교 통계학과)
  • Received : 2020.08.24
  • Accepted : 2020.09.08
  • Published : 2020.10.31

Abstract

This study focuses on the prediction and factors of apartment prices in Seoul using a convolutional neural networks (CNN) model that has shown excellent performance as a predictive model of image data. To do this, we consider natural environmental factors, infrastructure factors, and social economic factors of the apartments as input variables of the CNN model. The natural environmental factors include rivers, green areas, and altitudes of apartments. The infrastructure factors have bus stops, subway stations, commercial districts, schools, and the social economic factors are the number of jobs and criminal rates, etc. We predict apartment prices and interpret the factors for the prices by converting the values of these input variables to play the same role as pixel values of image channels for the input layer in the CNN model. In addition, the CNN model used in this study takes into account the spatial characteristics of each apartment by describing the natural environmental and infrastructure factors variables as binary images centered on each apartment in each input layer.

본 연구는 이미지 데이터에 대한 예측 모형으로 뛰어난 성능을 보여온 convolutional neural networks (CNN) 모형을 이용하여 서울 아파트 가격의 예측과 서울 각 지역 아파트들의 가격결정요인들을 연구한다. 이를 위해 강, 녹지, 고도와 같은 자연환경요인, 버스정류장, 지하철역, 상권, 학교 등과 같은 기반시설요소, 일자리수, 범죄율 등의 사회경제요소들을 설명변수로 고려하고, CNN 모형이 이미지 데이터에 좋은 성능을 보여온 것을 기반으로 이 설명변수들의 값들을 CNN 모형 입력층으로써 이미지 채널의 픽셀값과 같은 역할을 하도록 변환하여 아파트 가격의 예측과 가격결정요인에 대한 해석을 시도한다. 덧붙여 본 연구에서 사용된 CNN 모형은 자연환경요인과 기반시설요인 변수들을 각 아파트를 중심으로 하는 각 입력층의 채널에 이진의 이미지로 표현함으로써 각 아파트의 공간적인 특성을 고려할 수 있다.

Keywords

References

  1. Abadi, M., Agarwal, A., and Barham, P., et al. (2015). TensorFlow: Large-scale machine learning on heterogeneous systems. Available from: https://tensorflow.org
  2. Choi, C. S. (2010). A study on the existence of price bubbles in Korean housing market, Journal of the Korea Real Estate Society, 32, 177-199.
  3. Hasan, M., Ullah, S., Khan, M. J., and Khurshid, K. (2019). Comparative analysis of SVM, ANN and CNN for classifying vegetation species using hyperspectral thermal infrared data, The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-2/W13.
  4. Lim, S. S. (2014). A study on the forecasting models using housing price index, Journal of the Korean Data & Information Science Society, 25, 65-76. https://doi.org/10.7465/jkdi.2014.25.1.65
  5. Pebesma, E. J. and Bivand, R. S. (2005). Classes and methods for spatial data in R, R News, 5. Available from: https://cran.r-project.org/doc/Rnews/.
  6. Wickham, H. (2017). tidyverse: Easily install and load the 'Tidyverse'. R package version 1.2.1. https://CRAN.R-project.org/package=tidyverse.
  7. Yoo, C., Han, D., Im, J., and Bechtel, B. (2019). Comparison between convolutional neural networks and random forest for local climate zone classification in mega urban areas using Landsat images, ISPRS Journal of Photogrammetry and Remote Sensing, 157, 155-170. https://doi.org/10.1016/j.isprsjprs.2019.09.009
  8. Yoo, J.-S., Lim, K.-C., and Kie, S.-D. (2007). The empirical analysis of the bubble in housing price and land price, Journal of Industrial Economics and Business, 20, 2245-2264.
  9. Yu, L., Jiao, C., Xin, H., Wang, Y., and Wang, K. (2018). Prediction on housing price based on deep learning, International Journal of Computer and Information Engineering, 12, 90-99.
  10. Zhang, F., Du, B., and Zhang, L. (2017). A multi-task convolutional neural network for mega-city analysis using very high resolution satellite imagery and geospatial data. arXiv preprint arXiv:1702.07985.