공간적 상관성을 고려한 딥러닝 기반 부동산 가격 예측 방법 제안 = A Proposal of Real Estate Valuation Prediction Method using Deep Learning-based Spatial Regression Analysis

국문 초록 (Abstract)

부동산은 공간적인 특성을 가지고 있다는 점에서 다른 자산과 차별되는 특성을 갖는다. 공간적인 측면으로 접근하여, 본 연구에서의 데이터는 2013년 1분기부터 2023년 2분기까지의 서울시 3,000세대 이상의 아파트 단지이며, 방법론은 딥러닝 기반의 시계열 분석 기법인 RNN, LSTM, GRU이다. 이를 통해 3,000세대 이상의 아파트 단지들이 특정 지역구의 아파트 단지 가격에 어느 정도 영향을 미치는 지 확인할 수 있다. 모델별 평균 정확도를 MAPE를 통해 산출한 결과, RNN이 10.91, LSTM이 11.44, GRU가 11.12로서 RNN이 가장 우수했고, LSTM과 GRU가 비슷하였다. 추후 본 연구에서 제안하는 모형을 활용하여 높은 정확도의 부동산 가격 예측을 하는데 도움이 될 것으로 기대한다.

다국어 초록 (Multilingual Abstract)

Real estate has a characteristic that is differentiated from other assets in that it has spatial characteristics. Approaching from a spatial aspect, the data in this study are apartment complexes with more than 3,000 households in Seoul from the first quarter of 2013 to the second quarter of 2023, and the methodologies are RNN, LSTM, and GRU which are deep learning-based time series analysis techniques. As a result of calculating the average accuracy of each model through MAPE, RNN was 10.91, LSTM was 11.44, and GRU was 11.12. RNN was the best, and LSTM and GRU were similar. With the proposed model, it is expected to be helpful in predicting real estate valuation with higher accuracy in the future.

참고문헌 (Reference)

1 "dProgrammer lopez"

2 "Transaction Price Open System"

3 H. James, "The reliability of artificial neural networks for property data analysis" eres1996_157-, 1996

4 R. G. Ridker, "The determinants of residential property values with special reference to air pollution" 49 (49): 246-257, 1967

5 D. Chicco, "The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation" 7 : 1-24, 2021

6 이창로 ; 김세형, "The Deep Learning Approach to Property Valuation : An Application of a Multilayer Neural Net Model for Estimating House" 30 (30): 179-201, 2018

7 김희상 ; 주기훈 ; 임현승, "Product Category Classification using Word Embedding and GRUs" 19 (19): 11-18, 2021

8 L. Yu, "Prediction on housing price based on deep learning" 12 (12): 90-99, 2018

9 이태형 ; 전명진, "Prediction of Seoul House Price Index Using Deep Learning Algorithms with Multivariate Time Series Data" 8 (8): 39-56, 2018

10 배성완 ; 유정석, "Predicting the Real Estate Price Index Using Machine Learning Methods and Time Series Analysis Model" 26 (26): 107-133, 2018

11 배성완 ; 유정석, "Predicting the Real Estate Price Index Using Deep Learning" 27 (27): 71-86, 2017

12 N. Nguyen, "Predicting housing value : A comparison of multiple regression analysis and artificial neural networks" 22 (22): 313-336, 2020

13 A. S. Temur, "Predicting housing sales in Turkey using ARIMA, LSTM and hybrid models" 20 (20): 920-938, 2019

14 S. McGreal, "Neural networks : the prediction of residential values" 16 (16): 57-70, 1998

15 A. Khalafallah, "Neural network based model for predicting housing market performance" 13 (13): 325-328, 2008

16 "K-apt"

17 C. D. Lewis, "Industrial and business forecasting methods : a practical guide to exponential smoothing and curve fitting" Butterworth Scientific 40-, 1982

18 H. Ragb, "Hybrid GRU-LSTM Recurrent Neural Network-Based Model for Real Estate Price Prediction"

19 김진석 ; 김경민, "How the Pattern Recognition Ability of Deep Learning Enhances Housing Price Estimation" 25 (25): 183-201, 2022

20 B. Afonso, "Housing prices prediction with a deep learning and random forest ensemble" 389-400, 2019

21 X. Chen, "House price prediction using LSTM"

22 A. C. Goodman, "Hedonic prices, price indices and housing markets" 5 (5): 471-484, 1978

23 G. Milunovich, "Forecasting Australia's real house price index : A comparison of time series and machine learning methods" 39 (39): 1098-1118, 2020

24 배성완 ; 유정석, "Estimation of the Apartment Housing Price Using the Machine Learning Methods : The Case of Gangnam-gu, Seoul" 24 (24): 69-85, 2018

25 D. M. Grether, "Determinants of real estate values" 1 (1): 127-145, 1974

26 "Deep Learning Bible"

27 이주미 ; 박성훈 ; 조상호 ; 김주형, "Comparison of Models to Forecast Real Estates Index Introducing Machine Learning" 37 (37): 191-199, 2021

28 A. B. Khamis, "Comparative study on estimate house price using statistical and neural network model" 3 (3): 126-131, 2014

29 P. Rossini, "Artificial neural networks versus multiple regression in the valuation of residential property" 3 (3): 1-12, 1997

30 R. A. Borst, "Artificial neural networks in mass appraisal" 1 (1): 5-15, 1995

31 J. G. Mora-Esperanza, "Artificial intelligence applied to real estate valuation : An example for the appraisal of Madrid" 1 : 255-265, 2004

32 A. Evans, "Artificial Neural Networks : An Application to Residential Valuation in the UK" University of Portsmouth, Department of Economics 1992

33 S. W. Min, "A study on the forecasting of housing price using deep learning : focusing on apartment price index in Seoul" Gangnam University 2016

34 A. Q. Do, "A neural network approach to residential property appraisal" 58 (58): 38-45, 1992

35 G. E. Hinton, "A fast learning algorithm for deep belief nets" 18 (18): 1527-1554, 2006

36 R. F. Engle, "A dynamic model of housing price determination" 28 (28): 307-326, 1985

37 김경민 ; 김규석 ; 남대식, "A Study on the Index Estimation of Missing Real Estate Transaction Cases Using Machine Learning" 25 (25): 171-181, 2022

38 정원구 ; 이상엽, "A Study on the Forecasting of the Apartment Price Index Using Artificial Neural Networks" 14 (14): 39-64, 2007

39 성주한 ; 정상철, "A Study on the Factors Affecting Apartment Price in Seoul and Provinces" 78 (78): 92-103, 2019

40 남영우 ; 이정민, "A Study on the Applicability of Neural Network Model for Prediction of the Apartment Market" 7 (7): 162-170, 2006

41 전해정 ; 양혜선, "A Study on Prediction of Housing Price Using Deep Learning" 17 (17): 37-49, 2019

42 김태훈 ; 홍한국, "A Study on Apartment Price Models Using Regression Model and Neural Network Model" 43 : 193-200, 2004

43 C. W. Kim, "A Prediction of the Apartment Sales Price Using Deep Learning" 463-464, 2020