한국정보통신학회논문지 (Journal of the Korea Institute of Information and Communication Engineering)

  • 제25권12호
  • /
  • Pages.1739-1748
  • /
  • 2021
  • /
  • 2234-4772(pISSN)
  • /
  • 2288-4165(eISSN)
한국정보통신학회 (The Korea Institute of Information and Commucation Engineering)
권호 표지
DOI QR코드

DOI QR Code

Autoencoder 기법을 활용한 부동산 가격 이상치 분석

Analsis Of Outliers In Real Estate Prices Using Autoencoder

  • Kim, Yoonseo (Department of Business Administration, Sungkyunkwan University) ;
  • Park, Jongchan (Department of Economics, Sungkyunkwan University) ;
  • Oh, Hayoung (College of Computing and Informatics, Sungkyunkwan University)
  • 투고 : 2021.09.16
  • 심사 : 2021.10.11
  • 발행 : 2021.12.31
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

부동산 가격은 국가, 기업, 가계에 영향을 미치며 최근 급등하는 부동산 가격에 부동산 버블에 관한 연구가 많이 시행되고 있다. 하지만 부동산 버블 예측에서 단순히 부동산 가격만을 비교하거나, 부동산 매매에서 핵심적인 심리적 변수를 반영하지 못한다면 버블 예측 모형의 정확성이 떨어진다 판단할 수 있다. 본 연구는 오토인코더 기법을 사용하여 지역별 부동산 버블 상황을 설명할 수 있는 예측 모형을 설계하는 것이 목적이다. 기존의 부동산 버블 분석 연구들이 가격에 영향을 미치는 다양한 종류의 변수를 설정하지 못하였고 주로 선형 모형을 기반으로 연구를 진행했다는 부분에서, 본 연구는 기존 부동산 버블 연구에 사용되지 않았던 기법과 변수들의 도입 가능성을 시사한다.

Real estate prices affect countries, businesses, and households, and many studies have been conducted on the real estate bubble in recent soaring real estate prices. However, if the real estate bubble prediction simply compares the real estate price, or if it does not reflect key psychological variables in real estate sales, it can be judged that the accuracy of the bubble prediction model is poor. The purpose of this study is to design a predictive model that can explain the real estate bubble situation by region using the autoencoder technique. Existing real estate bubble analysis studies failed to set various types of variables that affect prices, and most of them were conducted based on linear models. Thus, this study suggests the possibility of introducing techniques and variables that have not been used in existing real estate bubble studies.

키워드

과제정보

Following are results of a study on the "Convergence and Open Sharing System" Project, supported by the Ministry of Education and National Research Foundation of Korea.

참고문헌

  1. S. W. Bae and J. S. Yu, "Predicting the Real Estate Price Index Using Machine Learning Methods and Time Series Analysis Model," Housing Studies Review, vol. 26, no. 1, pp. 107-133, Feb. 2018.
  2. C. H. Jung, "A Study on the Estimation of the Housing Market Bubble by Region," Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology, vol. 9, no. 10, pp. 891-900, Oct. 2019. https://doi.org/10.35873/ajmahs.2019.9.10.076
  3. W. H. Kim and W. C. Kang, "Study on the Real Estate Bubble Measurement -Focusing on Apartments-," Journal of the KRSA, vol. 28, no. 2, pp. 129-142, Jun. 2012.
  4. K. H. Kim, D. Y. Yang, and E. J. Kang, "Global Real Estate Price analysis Using Big Data," World Economy Today, vol. 19, no. 10, May. 2019.
  5. B. H. Kim, "A Further Investigation of House Price Bubbles in Korea: Kalman Filter Approach," Social Studies, vol. 6, no. 1, pp. 147-180, 2005.
  6. H. J. Chun, "An Empirical Study on the Estimate of Rational Real Estate Bubble in Korea," Journal of the Economic Geographical Society of Korea, vol. 17, no. 1, pp. 147-159, 2014. https://doi.org/10.23841/egsk.2014.17.1.147
  7. Y. T. Hwang, "A Study on the Estimation of Apartment Price Index: Focused on the Machine Learning Algorithm," Journal of money & finance, vol. 33, no. 3, pp. 51-83, Sep. 2019. https://doi.org/10.21023/jmf.33.3.3
  8. H. J. Chun, "Analysis of Factors Influencing the Retail Property Auction Price Ratio Using the Bayesian Network Approach," Journal of the Korea Real Estate Management Review, vol. 21, pp. 259-277, Jun. 2020. https://doi.org/10.37642/JKREMR.2020.21.11