Journal of the Architectural Institute of Korea (대한건축학회논문집)

Architectural Institute of Korea (대한건축학회)
권호 표지
DOI QR코드

DOI QR Code

Comparison of Models to Forecast Real Estates Index Introducing Machine Learning

머신러닝을 이용한 부동산 지수 예측 모델 비교

  • 이주미 (한양대학교 일반대학원 건축공학과) ;
  • 박성훈 ((주)다인그룹엔지니어링건축사사무소) ;
  • 조상호 ((주)토문엔지니어링건축사사무소) ;
  • 김주형 (한양대학교 건축공학부)
  • Received : 2020.09.14
  • Accepted : 2021.01.18
  • Published : 2021.01.30
⟨ Previous Next ⟩

Abstract

As the real estates occupy major portion of domestic households assets, relevant issue has been dealt seriously by the Korean government. However, apartment prices in downtown Seoul, the capital city, have soared despite various policies. Forecasting the real estate market trend has become an important research topic in order to provide information for establishing policies. In the prediction of the real estate market in the previous studies, two research directions were classified as follows: quantitative economic models and machine learning models. Regarding this trend, there was a need for comparative research on machine learning models, emerging methods, that are used to compare and predict various real estate indices. In this study, the machine learning model RF(Random Forest), XGBoost(eXtreme Gradient Boosting), and LSTM (Long Short Term Memory) are used to select suitable machine learning models for selected real estate index and conduct a comparative study to validate predictive power of machine learning models. Apartment sales index, land price index, charter price index, and real estate psychological index using univariate variables are predicted. In addition, RF, XGBoost and LSTM models all tended to be generally marginal with RMSE values of 0.0268, 0.0296, and 0.0259 in charter(Jeonse), Korean traditional pre-deposit rental system, price index data with linear but small variants. This shows that the prediction of the real estate index is deviated from the prediction accuracy of machine learning models depending on the periodic characteristics and data characteristics of the real estate index.

Keywords

References

  1. Bae, S., & Yoo, J. (2017). Predicting the Real Estate Price Index Using Deep Learning, Korea Real Estate Review, 27(3), 71-86.
  2. Bae, S., & Yoo, J. (2018). Predicting the Real Estate Price Index Using Machine Learning Methods and Time Series Analysis Model, Korean Association For Housing Policy Studies, 26(1), 107-133. https://doi.org/10.24957/hsr.2018.26.1.107
  3. Bae, S. (2019). Forecasting Property Prices Using the Machine Learning Methods: Model Comparisons, Doctoral dissertation, Dan-Kook University.
  4. Brownlee, J. (2017). Long short-term memory networks with python, 1.5, Machine learning mastery.
  5. Cao, Q., Ewing, B.T., & Thompson, M.A. (2012). Forecasting wind speed with recurrent neural networks, European Journal of Operational Research, 221(1), 148-154. https://doi.org/10.1016/j.ejor.2012.02.042
  6. Jain, K., & Payal. (2011). A review study on urban planning & artificial intelligence, International Journal of Soft Computing and Engineering (IJSCE), 1(5), 101-104.
  7. Jang, Y. (2018). An Analysis of Non-linear Effects of Impact Factors on Housing Price, Journal of The Korean Data Analysis Society, 20(6), 2953-2966. https://doi.org/10.37727/jkdas.2018.20.6.2953
  8. KAB. (2020). Apartment Housing Actual Transaction Price Index Statistical Information Report.
  9. KAB. (2020). National Land Price Change Rate Survey Statistical Information Report.
  10. Kim, I., & Lee, K. (2020). Tree based ensemble model for developing and evaluating automated valuation models: The case of Seoul residential apartment, journal of the korean data information science society 2020, 31(2), 375-389. https://doi.org/10.7465/jkdi.2020.31.2.375
  11. KRIHS. (2020). Real Estate Market Consumer Psychological Survey Guidelines.
  12. Lee, C. (2015). Estimating single-family house prices using non-parametric spatial models and an ensemble learning approach, Doctoral dissertation, Seoul National University.
  13. Lee, T. (2019). Prediction of Seoul House Price Index Using Artificial Neural Network, Doctoral dissertation, Chung-Ang University.
  14. Min, S., & Seo, C. (2017). An Analysis on the Real Estate Field Research Trends and Characteristic - Focused on the Text Mining Techniques -, Korea Real Estate Academy Review, 69, 102-115.
  15. Min, S. (2016). Gangnam and Non-Gangnam Housing Prcie Index Forecast Using Deep Learning - Focused on Housing Policy, Doctoral dissertation, Gang-Nam University.
  16. Moon, K. (1997). Prediction of Seoul House Price Index Using Deep Learning Algorithms with Multivariate Time Series Data, Journal of The Korean Official Statistics, 2(1), 23-56.
  17. Moon, S., Jang, S., Lee, J., & Lee, J. (2016). Machine learning and deep learning technology trends, Information & communications magazine, 33(11), 49-56.
  18. Na, D. (2019). Machine learning algorithm and IoT technique research for animal welfare smart farm, Doctoral dissertation, Kon-Kuk University.
  19. Na, S., & Kim, J. (2019). A study on the sales price of apartment using public data : The apartment in Gangnam-gu Seoul, Journal of The Korean Cadastre Information Association, 21(1), 3-12. https://doi.org/10.46416/jkcia.2019.04.21.1.3
  20. Numbeo. (2019). Cost of Living Comparison, Retrieved June 20, 2019 from https://www.numbeo.com/cost-of-living/comparison.jsp
  21. Park, S. (2019). Analysis of Apartment Pricing Factors Using Machine Learning: Case of Busan Area, Thesis, Dong-a University.
  22. Shin, Y. (2017). A research on contract price prediction model for real estate auction based on Machine Learning Technology, Thesis, The Cyber University of Korea.