Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김주형 | - |
dc.date.accessioned | 2022-11-15T07:36:34Z | - |
dc.date.available | 2022-11-15T07:36:34Z | - |
dc.date.issued | 2021-01 | - |
dc.identifier.citation | 대한건축학회논문집, v. 37, NO. 1, Page. 191-199 | en_US |
dc.identifier.issn | 2733-6239;2733-6247 | en_US |
dc.identifier.uri | http://koreascience.or.kr/article/JAKO202110265883524.page | en_US |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/176897 | - |
dc.description.abstract | 서울의 부동산 가격은 다양한 정책에도 불안정한 추세를 보여 관련 대책 수립을 위한 가격 예측은 중요한 연구주제가 되었으며 최근에는 다양한 머신러닝 기법이 도입되어 비교 연구의 필요성이 제기된다. 이에 부동산 지수별 최적 머신러닝 예측 모델 선별과 예측력의 비교연구를 진행하기 위해 4가지의 부동산 지수와 3가지의 머신러닝 모델 RF, XGB, LSTM을 활용하였다. 연구결과 LSTM모델이 높은 예측 정확도를 보였고 RF, XGB, LSTM 모델 모두 선형적이며 작은 등락을 가지는 전세가격지수 데이터에서 예측력이 높았다. 이를 통해 부동산 지수의 예측은 부동산 지수의 주기특성과 데이터 형상에 따라 머신러닝 모델별 예측 정확도의 차이를 가지는 사실을 알 수 있다. 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 trendhas become an important research topic in order to provide information for establishing policies. In the prediction of the real estate market inthe previous studies, two research directions were classified as follows: quantitative economic models and machine learning models. Regardingthis trend, there was a need for comparative research on machine learning models, emerging methods, that are used to compare and predictvarious 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 comparativestudy to validate predictive power of machine learning models. Apartment sales index, land price index, charter price index, and real estatepsychological index using univariate variables are predicted. In addition, RF, XGBoost and LSTM models all tended to be generally marginalwith RMSE values of 0.0268, 0.0296, and 0.0259 in charter(Jeonse), Korean traditional pre-deposit rental system, price index data with linearbut small variants. This shows that the prediction of the real estate index is deviated from the prediction accuracy of machine learningmodels depending on the periodic characteristics and data characteristics of the real estate index. | en_US |
dc.language | ko | en_US |
dc.publisher | 대한건축학회 | en_US |
dc.subject | 부동산 지수 예측 | en_US |
dc.subject | 머신러닝 | en_US |
dc.subject | 장단기메모리 | en_US |
dc.subject | Real Estates Index Forecasting | en_US |
dc.subject | Machine Learning | en_US |
dc.subject | Long Short-Term Memory | en_US |
dc.title | 머신러닝을 이용한 부동산 지수 예측 모델 비교 | en_US |
dc.title.alternative | Comparison of Models to Forecast Real Estates Index Introducing Machine Learning | en_US |
dc.type | Article | en_US |
dc.relation.no | 1 | - |
dc.relation.volume | 37 | - |
dc.identifier.doi | 10.5659/JAIK.2021.37.1.191 | en_US |
dc.relation.page | 191-199 | - |
dc.relation.journal | 대한건축학회논문집 | - |
dc.contributor.googleauthor | 이주미 | - |
dc.contributor.googleauthor | 박성훈 | - |
dc.contributor.googleauthor | 조상호 | - |
dc.contributor.googleauthor | 김주형 | - |
dc.sector.campus | S | - |
dc.sector.daehak | 공과대학 | - |
dc.sector.department | 건축공학부 | - |
dc.identifier.pid | kcr97jhk | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.