Predicting the Real Estate Price Index Using Deep Learning (딥 러닝을 이용한 부동산가격지수 예측)

Seong-Wan Bae, (배성완); Jung-Suk Yu (유정석)

Predicting the Real Estate Price Index Using Deep Learning

Korea Real Estate Review
2017, 27(3), pp.71-86
Publisher : korea real estate research institute
Research Area : Social Science > Law > Law of Special Parts > Law of Real Estate
Published : September 30, 2017

Seong-Wan Bae, ¹, Jung-Suk Yu ¹

¹단국대학교

Accredited

ABSTRACT

The purpose of this study was to apply the deep running method to real estate price index predicting and to compare it with the time series analysis method to test the possibility of its application to real estate market forecasting. Various real estate price indices were predicted using the DNN (deep neural networks) and LSTM (long short term memory networks) models, both of which draw on the deep learning method, and the ARIMA (autoregressive integrated moving average) model, which is based on the time seies analysis method. The results of the study showed the following. First, the predictive power of the deep learning method is superior to that of the time series analysis method. Second, among the deep learning models, the predictability of the DNN model is slightly superior to that of the LSTM model. Third, the deep learning method and the ARIMA model are the least reliable tools for predicting the housing sales prices index among the real estate price indices. Drawing on the deep learning method, it is hoped that this study will help enhance the accuracy in predicting the real estate market dynamics.

KEYWORDS

deep learning, real estate price index, predicting, DNN, LSTM

Citation status

* References for papers published after 2023 are currently being built.

[journal] 김근용 / 1998 / 주택가격 예측을 위한 모형설정과 검정 / 국토 / 국토연구원 197 : 54~61

[confproc] 김성환 / 2016 / 주택경기 예측 향상을 위한 시계열모형 구축 / 2016년 한국주택학회 상반기 학술대회 발표자료집 / 한국주택학회 : 33~49

[journal] 김양훈 / 2016 / LSTM Language Model Based Korean Sentence Generation / 한국통신학회논문지 / 한국통신학회 41(5) : 592~601

[journal] 남경두 / 1997 / 부동산 분석을 위한 뉴럴네트웍의 응용 / 상경연구 / 건국대학교 경제경영연구소 22(2) : 187~201

[thesis] 민성욱 / 2017 / 딥러닝을 이용한 주택가격 예측모형 연구 / 박사 / 강남대학교

[journal] 손정식 / 2003 / A Study on the Forecasting Model of Real Estate Market : The Case of Korea / 주택연구 / 한국주택학회 11(1) : 49~75

[confproc] 송사광 / 2016 / 딥러닝 기반 날씨와 소상공인 매출 연계빅데이터 분석 / 한국기상학회 학술대회 논문집 / 한국기상학회 : 489~290

[journal] 안성만 / 2016 / Deep Learning Architectures and Applications / 지능정보연구 / 한국지능정보시스템학회 22(2) : 127~142

[journal] 안성만 / 2017 / Korean Sentence Generation Using Phoneme-Level LSTM Language Model / 지능정보연구 / 한국지능정보시스템학회 23(2) : 71~88

[confproc] 이세희 / 2016 / RNN을 이용한 고객 이탈 예측 및분석 / 한국컴퓨터정보학회 학술발표논문집 / 한국컴퓨터정보학회 24(2) : 45~48

[journal] 이용만 / 2008 / Smoothing in the Korean KB-Housing Price Index / 주택연구 / 한국주택학회 16(4) : 27~47

[journal] 이우식 / 2017 / A deep learning analysis of the KOSPI’s directions / 한국데이터정보과학회지 / 한국데이터정보과학회 28(2) : 287~295

[journal] 이우식 / 2016 / A deep learning analysis of the Chinese Yuan’s volatility in the onshore and offshore markets / 한국데이터정보과학회지 / 한국데이터정보과학회 27(2) : 327~335

[journal] 이형욱 / 2009 / Comparative Analysis for Predictability of Housing Price Index by Model in Seoul / 부동산학보 / 한국부동산학회 (38) : 215~235

[journal] 임성식 / 2014 / A study on the forecasting models using housing price index / 한국데이터정보과학회지 / 한국데이터정보과학회 25(1) : 65~76

[journal] 정원구 / 2007 / A Study on the Forecasting of the Apartment Price Index Using Artificial Neural Networks / 주택연구 / 한국주택학회 15(3) : 39~64

[report] 최근우 / 2016 / 딥러닝(Deep Learning)기술의 이해와 연구개발 정책과제 / 한국과학기술기획평가원

[confproc] 최승현 / 2016 / 딥러닝 기법을 이용한 아스팔트포장의 공용수명예측 / 대한토목학회 학술대회 / 대한토목학회 10 : 7~8

[journal] 하지훈 / 2016 / Forecasting the Precipitation of the Next Day Using Deep Learng / 한국지능시스템학회 논문지 / 한국지능시스템학회 26(2) : 93~98

[journal] Bergstra, J. / 2012 / Random Search for Hyper-Parameter Optimization / Journal of Machine Learning Research / JMLR 13 : 281~305

[journal] Chakraborty, K. / 1992 / Forecasting the behavior of multivariate time series using neural networks / Neural networks / Elsevier 5(6) : 961~970

[confproc] Glorot, X. / 2010 / Understanding the difficulty oftraining deep feedforward neural networks / Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, PMLR 9 : 249~256

[confproc] Glorot, X. / 2011 / Deep Sparse Rectier Neural Networks / Proceedings of the 14th International Conference on Artificial Intelligence and Statistics : 315~323

[confproc] He, Kaiming / 2015 / Delving Deep into Rectifers: Surpassing Human-Level Performance on ImageNet Classification / The IEEE International Conference on Computer Vision (ICCV) / Computer Vision Foundation : 1026~1034

[journal] Hinton, G. E. / 2006 / A Fast Learning Algorithm for Deep Belief Nets / Neural Computation / MIT Press 18(7) : 1527~1554

[journal] Hochreiter, S. / 1997 / Long short-term memory / Neural Computation / MIT Press 9(8) : 1735~1780

[journal] Kaastra, I. / 1996 / Designing a neural network for forecasting financial and economic time series / Neurocomputing / Elsevier Science B. V 10 : 215~236

[confproc] Kennedy, J. / 1995 / Particle swarm optimization / Proceedings of the IEEE International Conference on Neural Networks : 1942~1948

[confproc] Kingma, D. P. / 2015 / ADAM: A Methoe for Stochastic Optimization / The 3rd International Conference for Learning Representations : 1~15

[journal] Kuremotoa, T. / 2014 / Time series forecasting using a deep belief network with restricted Boltzmann machines / Neurocomputing / Elsevier 137 : 47~56

[journal] McCulloch, W. S. / 1943 / A logical calculus of the ideas immanent in nervous activity / The Bulletin of Mathematical Biophysics / Springer 5(4) : 115~133

[book] Minsky, M. / 1969 / Perceptrons / M.I.T. Press

[confproc] Nair, V. / 2010 / Rectified Linear Units Improve Restricted Boltzmann Machines / Proceedings of the 27 th International Conference on Machine Learning (ICML) : 807~814

[book] Rumelhart, D. E. / 1986 / Parallel Distributed Processing Explorations in the Microstructure of Cogniton Vol1 / The MIT Press

[confproc] Vincent, P. / 2008 / Extracting and composing robust features with denoising autoencoders / proceedings of the 25th international conference on Machine learning( ICML) : 1096~1103

[journal] Zhang, G. P. / 2003 / Time series forecasting using a hybrid ARIMA and neural network model / Neurocomputing / Elsevier 50 : 157~175

[other] 한국감정원 / 2015 / 한국감정원⋅한국거래소 「부동산 금융상품 투자지수 공동개발」을 위한 업무 협약식 개최 / 보도자료(2015.12.14)

[web] / 파이썬 딥러닝 라이브러리 / https://keras.io

[web] / 한국감정원 부동산통계정보 / www.r-one.co.kr

KJCKorea
Journal Central

Korea Real Estate Review 2023 KCI Impact Factor : 0.56