Journal of the Korea Academia-Industrial cooperation Society (한국산학기술학회논문지)

The Korea Academia-Industrial cooperation Society (한국산학기술학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Housing Price Index Using Artificial Neural Network

인공신경망을 이용한 주택가격지수 예측

  • Received : 2021.02.09
  • Accepted : 2021.04.02
  • Published : 2021.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

Real estate market participants need to have a sense of predicting real estate prices in decision-making. Commonly used methodologies, such as regression analysis, ARIMA, and VAR, have limitations in predicting the value of an asset, which fluctuates due to unknown variables. Therefore, to mitigate the limitations, an artificial neural was is used to predict the price trend of apartments in Seoul, the hottest real estate market in South Korea. For artificial neural network learning, the learning model is designed with 12 variables, which are divided into macro and micro factors. The study was conducted in three ways: (Ed note: What is the difference between case 1 and 2? Is case 1 micro factors?)CASE1 with macro factors, CASE2 with macro factors, and CASE3 with the combination of both factors. As a result, CASE1 and CASE2 show 87.5% predictive accuracy during the two-year experiment, and CASE3 shows 95.8%. This study defines various factors affecting apartment prices in macro and microscopic terms. The study also proposes an artificial network technique in predicting the price trend of apartments and analyzes its effectiveness. Therefore, it is expected that the recently developed learning technique can be applied to the real estate industry, enabling more efficient decision-making by market participants.

부동산의 시장 참여자들에게 부동산 가격에 대한 방향성을 예측하는 것은 의사결정에 있어서 매우 중요하다. 이를 위해 주로 회귀분석, ARIMA, VAR 등의 방법론을 사용하는데 이는 불특정 변수에 의해서 변동하는 자산의 가치를 예측하는데 한계점을 갖는다. 때문에 본 연구에서는 이를 보완하기 위해서 인공신경망 기법을 이용해 부동산 시장에서 유동성이 풍부한 서울 아파트 가격 추이를 예측하고자 한다. 인공신경망 학습을 위해서 총 12개의 거시 및 미시적 변수를 나눠 학습 모형을 설계하는데 거시적 요인은 CASE1, 미시적 요인은 CASE2 그리고 두 요인을 조합해서 요인을 구성한 CASE3 으로 나눠서 실험한다. 그 결과 CASE1 과 CASE2 는 약 2년 동안 87.5%의 예측을 보이고 CASE3은 95.8%의 예측성과를 보인다. 본 연구는 아파트 가격에 영향을 주는 다양한 요인들을 거시적 및 미시적으로 구분하여 정의하고 미래의 아파트 가격의 방향성을 예측하는데 인공신경망 기법을 제안하고 그 실효성을 분석했다. 따라서 최근 발전하고 있는 학습 기법이 부동산 분야에 다양한 관점으로 적용되어 시장 참여자들의 효율적인 의사결정을 할 수 있기를 기대한다.

Keywords

References

  1. D. W. Kim, "Do Households Own Too Much of Housing Asset? An Analysis of Investment Return of Housing Asset", Journal of Korean Economic Analysis, Vol.23, No.3, pp.171-236, Nov. 2017. DOI: http://dx.doi.org/10.22823/jkea.23.3.201712.171
  2. M. H. Jang and H. S. Kim, "A Research on Fluctuations of Housing Prices Using Text Mining", Journal of Korean Economic Analysis, Vol.30, No.2, pp.35-42, Apr. 2019. DOI: https://doi.org/10.6107/JKHA.2019.30.2.035
  3. S. S. Lim, "A study on the forecasting models using housing price index", The Korean Data and Information Science Society, Vol.25, No.1, pp.65-76, Jan. 2014. DOI: http://dx.doi.org/10.7465/jkdi.2014.25.1.65
  4. C. H. Lee, "A Bayesian Variable Selection Method for Seoul Apartment Price Index Prediction", The Korean Economic Association, Vol.68, No.1, pp.153-190, Mar. 2020. DOI: http://dx.doi.org/10.22841/kjes.2020.68.1.005
  5. W. J. Lee, C. Y. Park, "Prediction of apartment prices per unit in Daegu-Gyeongbuk areas by spatial regression models", The Korean Data and Information Science Society, Vol.26, No.3, pp.561-568, May. 2015. DOI: https://doi.org/10.7465/jkdi.2015.26.3.561
  6. H. J. Lee, "Prediction and factors of Seoul apartment price using convolutional neural networks", The Korean Journal of applied Statistics, Vol.33, No.5, pp.603-614, Oct. 2020. DOI: https://doi.org/10.5351/KJAS.2020.33.5.603
  7. H. J. Chun, "Effects of Macroeconomic Variables on Regional Housing Prices Using Bayesian Panel VAR Model", Asia Culture Academy of Incorporated Association, Vol.10, No.6, pp.1349-1362, Dec. 2019. DOI: https://doi.org/10.22143/HSS21.10.6.100
  8. T. H. Kim, H. H. Kuk, "A Study on Apartment Price Models Using Regression Model and Neural Network Model Taehun Kim and Hankuk Hong", The Korea Spatial Planning Review , Vol.43, pp.183-200, Dec. 2004.
  9. T. H. Lee and M. J. Jun, "Prediction of Seoul House Price Index Using Deep Learning Algorithms with Multivariate Time Series Data", SH Urban Research & Insight, Vol.8, No.2, pp.39-57, Aug. 2018. DOI: https://doi.org/10.26700/shuri.2018.08.8.2.39
  10. S. M. Warren and P. Walter, "A logical calculus of the ideas immanent in nervous activity", Bulletin of mathematical biophysics, Vol.5, pp.115-133, Dec. 1943. DOI: https://doi.org/10.1007/BF02478259
  11. P. R. Burrell and B. O. Folarin, "The impact of neural networks in finance", Neural Computing & Applications, Vol.6, pp.193-200, Dec. 1997. DOI: https://doi.org/10.1007/BF01501506
  12. J. P. Ryu, H. J. Shin, "Portfolio Selection Strategy Using Deep Learning", Korea Institute of Enterprise Architecture, Vol.15, No.1, pp.43-50, Mar. 2018. DOI: http://doi.org/10.22865/jita.2018.15.1.43
  13. S. Peterson and A. B. Flanagan, "Neural network hedonic pricing models in mass real estate appraisal", Journal of Real Estate Research, Vol.31, No.2, pp.147-164, Oct. 2009. DOI: http://doi.org/10.1007/978-1-4615-0909-7_9
  14. J. P. Ryu, H. J. Shin, "A Methodology for Hedging Equity Linked Warrant Using Artificial Neural Network", The Korea Academia-Industrial cooperation Society, Vol.13, No.13, pp.1091-1098, Mar. 2012. DOI: https://doi.org/10.5762/KAIS.2012.13.3.1091
  15. H. I. Jang, B. W. Lim and H. K. Kim, "Changes in the comovement of house price and Jeonse price in the Korean housing market considering the macroeconomic factors", Housing Studies, Vol.27, No.4, pp.89-124, Nov. 2019. DOI: http://dx.doi.org/10.24957/hsr.2019.27.4.89
  16. J. H. Sung, "An analysis of factors influencing the formation of apartment sale price in Changwon City : focused on the influence of unsold apartments", Residential Environment Institute Of Korea, Vol.17, No.1, pp.1-12, Mar. 2019. DOI: http://dx.doi.org/10.22313/reik.2019.17.1.1
  17. K. M. Kim, "A Study on Dynamic Correlations between the Seoul Apartment Market and Factors of Macroeconomic Variable", KOREA REAL ESTATE ACADEMY REVIEW, Vol.73, No.1, pp.115-129, May.