대한건축학회논문집 (Journal of the Architectural Institute of Korea)

  • 제40권1호
  • /
  • Pages.35-44
  • /
  • 2024
  • /
  • 2733-6239(pISSN)
  • /
  • 2733-6247(eISSN)
대한건축학회 (Architectural Institute of Korea)
권호 표지
DOI QR코드

DOI QR Code

Transformer와 LSTM을 순차적으로 적용하여 분석한 주택 가격 지수 예측 연구 - 문제점 분석 및 해결 전략을 중심으로 -

Investigating Problem Analysis and Solution Strategies in Predicting Housing Price Index Through Sequential Application of Transformer and LSTM Models

  • 투고 : 2023.10.27
  • 심사 : 2023.12.23
  • 발행 : 2024.01.30
⟨ 이전 논문 다음 논문 ⟩

초록

This study aims to review previous research on factors affecting the housing price index and construct a prediction model for the index using Long Short-Term Memory (LSTM) and Transformer models. Specifically, it combines LSTM, specialized in processing time-series data, and DistilBERT, specialized in handling text data, to utilize both historical housing price index data and relevant news articles. The experimental results of the proposed model confirmed significant accuracy when comparing predicted values in each region (J, S, G) with the actual values. However, some clusters displayed relatively high errors, indicating a need for additional analysis and improvement. Additionally, it was observed that subjective elements could significantly impact the interpretation of clustering results, highlighting the necessity for further analysis. Result visualization and statistical analysis were conducted, confirming their accurate reflection of housing price fluctuation trends in each region. This study introduces a novel approach to predicting the housing price index using deep learning models like LSTM and DistilBERT, providing valuable insights into real estate market trend predictions. The approaches and findings from this research are anticipated to provide valuable starting points for further exploration of creative solutions and the development of effective problem-solving strategies.

키워드

참고문헌

  1. Bae, S. W. (2019). Forecasting Property Prices Using the Machine Learning Methods : Model Comparisons, Ph. D. Dissertation, Dankook University.
  2. Bae, S. W., & Yu, J. S. (2018). Predicting the Real Estate Price Index Using Machine Learning Methods and Time Series Analysis Model. Housing Studies, 26(1), 107-133.
  3. Cheon, I. H. (2007). A Study on the Effect of Yang Tak Factor in the Housing Price- A Case of Haeundae New Town -. Korean Association for Housing policy Studies, 15(1), 99-126.
  4. Chun, H. J., & Yang, H. S. (2019). A Study on Prediction of Housing Price Using Deep Learning. Journal of The Residential Environment Institute of Korea, 17(2), 37-49. https://doi.org/10.22313/reik.2019.17.2.37
  5. Glorot, X., & Bengio, Y. (2010). Understanding the difficulty of training deep forward neural networks. In Proceedings of the International Conference on Artificial Intelligence and Statistics, Society for Artificial Intelligence and Statistics.
  6. Ham, J. Y., & Son, J. Y. (2022). Analysis of Housing Price Fluctuations Using Bayesian Approach. Journal of The Residential Environment Institute of Korea, 20(1), 1-21.
  7. Han, C. J. (2021). Study on Interpretable Transformer Model for Multi-step Stock Price Movement Forecasting, Thesis, Seoul National University.
  8. Hong, S. H. (2020). A Study on Stock Price Prediction System Based on Text Mining Method Using LSTM and Stock Market News. Journal of Digital Convergence, 18(7), 223-228. https://doi.org/10.14400/JDC.2020.18.7.223
  9. Jo, M. S., & Kim, T. H. (2013). A Study on Characteristics of Hedonic Price Models Based on Meta-regression Analysis. Journal of the Korean Data Analysis Society, 15(5), 2765-2780.
  10. Jais, I. K. M., Ismail, A. R., & Nisa, S. Q. (2019). Adam Optimization Algorithm for Wide and Deep Neural Network. Knowledge Engineering and Data Science, 2(1), 41-46.
  11. Jo, L. J., & Park, W. S. (2023). Effects of Loss Functions on the Performance of NeRF. Korean Institute of Next Generation Computing, 202-205.
  12. Kim, D. W. & Yoo, J. S. (2014). The Determinants of Housing Price Indices Volatility Using a Switching Regression Analysis. Housing Studies, 22(3), 69-99.
  13. Kim, G. G., Song, H. C., & Lee, J. H. (2010). A Study on the Determinants of the Change Rate of Housing Price by Areas. Review of Real Estate and Urban Studies, 3(1), 101-115.
  14. Kim, S. Y., Fang, X. Z., & Yoo, S. J. (2013). Causality Between Sales Price of Housing Index and Consumer Sentiment Index : Impact on Korea(South) and China. The Journal of Modern China Studies, 15(1), 175-210.
  15. Lee, M. S. (2023). A Study on the Relation between Inflation Expectations and House Prices: Comparison between South Korea and the U.S.. Journal of KREAA, 29(1), 7-36. https://doi.org/10.19172/KREAA.29.2.1
  16. Lee, S. W., & Lee, W. H. (2011). Refining Initial Seeds using Max Average Distance for K-Means Clustering. Jounal of Internet Computing and Services, 12(2), 103-111.
  17. Lee, S. J. (2019a). Segmentation of Housing Submarkets and Housing Price Prediction Through Data Mining. Journal of Environmental Studies, 64, 176-177.
  18. Lee, T. H. (2019b). Prediction of Seoul House Price Index Using Artificial Neural Network, Ph. D. Dissertation, Chung-Ang University.
  19. Ma, B. H. (2020). Natural Language Generation Using GAN and Transformer Models, ph. D. Dessertation, Ajou University.
  20. Milunovich, G. (2020). Forecasting Australia's real house price index: A comparison of time series and machine learning methods. Journal of forecasting, 1098-1118.
  21. Sanh, V., Debut, L., Chaumond, J., & Wolf, T. (2019). DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108.
  22. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. Advances in Neural Information Processing Systems, 30.
  23. Yoon, S. M., Sohn, S. H., & Lee, J. I. (2016). Empirical Analysis on the Long-Run and Short-Run Determinants of Regional House Price Dynamics. Korea Real Estate Academy Review, (67), 198-211.
  24. Yue, Y., Kim, W. H., & Cho, Y. S. (2023). Stock Market Prediction Based on LSTM Neural Networks. The Journal of International Trade & Commerce, 19(2), 391-407.