Journal of the Architectural Institute of Korea (대한건축학회논문집)

Architectural Institute of Korea (대한건축학회)
권호 표지
DOI QR코드

DOI QR Code

Long-term Prediction of Rebar Price Using Bidirectional Long Short-Term Memory and Time Series Cross-Validation

양방향 장단기 기억과 시계열 교차검증을 이용한 철근 가격의 장기예측에 관한 연구

  • Received : 2022.02.28
  • Accepted : 2022.05.09
  • Published : 2022.05.30
⟨ Previous Next ⟩

Abstract

This study proposes a long-term prediction method of rebar price using deep learning techniques such as a bidirectional long and short-term memory (Bi-LSTM), a recursive method, and a time series cross-validation. Among recurrent neural network (RNN) models, Bi-LSTM provides the best prediction performance for small time series data such as monthly rebar price when applied. The recursive method uses the short-term prediction result as an input value for predicting the next time point data, which can repeatedly be used for making long-term predictions. Time-series cross-validation enables more stable prediction accuracy by enhancing learning that may be lacking in small time series data. By applying these deep learning techniques, this study predicts the monthly rebar price for up to 5 months and compares it with the previous study. As a result, it has been found that the average accuracy increases, and the deviation of the predicted values decreases.

Keywords

Acknowledgement

이 논문은 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(No. 2021R1F1A1063286).

References

  1. Bae, S., & Yu, J. (2018). Predicting the real estate price index using machine learning methods and time series analysis model, Housing Studies Review, 26(1), 107-133.
  2. Bergstra, J., & Bengio, Y. (2012). Random search for hyper-parameter optimization, The Journal of Machine Learning Research, 13(1), 281-305.
  3. Choi, M., & Kwon, O. (2008). Construction material costincrease and countermeasures, Construction trend briefing by Korea Institute of Construction Industry, 6, 2-34.
  4. Choi, Y., Yim, H., & Park, B. (2009). Analysis on the Lotting Price Fluctuation of the Multi-Family Attached House According to the Construction Material Cost Variation, Journal of The Korean Society of Civil Engineers, 29(6D), 753-760.
  5. Geron, A. (2019). Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems (2E), O'Reilly, p.31.
  6. Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory, Neural computation, 9(8), 1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  7. Howard, R., & Matheson, J. (2005). Influence diagram retrospective, Decision Analysis, 2(3), 144-147. https://doi.org/10.1287/deca.1050.0050
  8. Index.go.kr (2022). Building permit and construction start status. accessed Jan 17, 2022, https://www.index.go.kr/potal/stts/idxMain/selectPoSttsIdxSearch.do?idx_cd=1224.
  9. Jeong, D. (2017). Trend on Artificial Intelligence Technology and Its Related Industry, Korea Institute of Information Technology Magazine, 15(2), 21-28. https://doi.org/10.14801/jkiit.2017.15.5.21
  10. Ji, S., Goo, Y., Baek, U., Park, J., & Yoon, S. (2019). LSTM Learning Data Selection Technique for Number of Bitcoin Transactions Prediction, KNOM Conference, Korea Information and Communications Society.
  11. Kang, M. (2020). Comparison of Gradient Descent for Deep Learning, Journal of the Korea Academia-Industrial cooperation Society, 21(2), 189-194. https://doi.org/10.5762/KAIS.2020.21.2.189
  12. Kim, B., Jung, S., Kim, M., Kim, J., Lee, & H., Kim, S. (2020). Solar Power Generation Forecasting based on LSTM considering Weather Conditions, Journal of Korean Institute of Intelligent Systems, 30(1), 7-12. https://doi.org/10.5391/jkiis.2020.30.1.7
  13. Kosis.kr (2022a). Producers price index (Rebar and bar). accessed Jan 17, 2022, https://kosis.kr/statHtml/statHtml.do?orgId=301&tblId=DT_013Y202&conn_path=I3.
  14. Kosis.kr (2022b). Import price indexes (Rebar and bar). accessed Jan 17, 2022, https://kosis.kr/statHtml/statHtml.do?orgId=301&tblId=DT_018Y301.
  15. Kosis.kr (2022c). Comprehensive raw material import trend. accessed Jan 17, 2022, https://kosis.kr/statHtml/statHtml.do?orgId=392&tblId=DT_AA12.
  16. Kosis.kr (2022d). Steel production (Rebar). accessed Jan 17, 2022, https://kosis.kr/statHtml/statHtml.do?orgId=363&tblId=TX_36301_A000.
  17. Kpi.or.kr (2022). Deformed reinforcing bar. accessed Jan 17, 2022, https://www.kpi.or.kr/www/price/detail_change.asp?CATE_CD=10100104&ITEM_SPEC_CD=10011.
  18. Lahari, M., Ravi, D., & Bharathi, R. (2018). Fuel Price Prediction Using RNN, International Conference on Advances in Computing, Communications and Informatics (ICACCI), IEEE, 1510-1514.
  19. Larochelle, H., Erhan, D., Courville, A., Bergstra, J., & Bengio Y. (2007). An empirical evaluation of deep architectures on problems with many factors of variation, Proceedings of the 24th International Conference on Machine Learning, 473-480.
  20. Lee, J., Yoo, J., Kim, C., Lee, G., & Lim, B. (2008). How to calculate the order point considering the fluctuations in demand for materials at construction sites, Journal of the Architectural Institute of Korea-Structural System, 24 (10), 117-125.
  21. Lee, D., & Kim, K. (2019). Deep Learning Based Prediction Method of Long-term Photovoltaic Power Generation Using Meteorological and Seasonal Information, Journal of Society for e-Business Studies, 24(1), 1-16. https://doi.org/10.20428/jss.v24i4.1445
  22. Lee, Y., & Kim, K. (2020). Experimental Study on the Expansion of the Short-term Prediction Range of Rebar Prices Using Deep Learning, Journal of The Architectural Institute of Korea, 36(12), 265-272. https://doi.org/10.5659/JAIK.2020.36.12.265
  23. Lee, M., Kim, J., & Jang, B. (2020). Chicken pox prediction using deep learning model, Transactions of the Korean Institute of Electrical Engineers, 69(1), 127-137. https://doi.org/10.5370/kiee.2020.69.1.127
  24. Lee, Y., & Kim, K. (2021). Experimental Study on Long-Term Prediction of Rebar Price Using Deep Learning Recursive Prediction Method, Korean Journal of Construction Engineering and Management, 22(3), 21-30. https://doi.org/10.6106/KJCEM.2021.22.3.021
  25. Lee, Y., Choi, Y., Cho, H., & Kim, J. (2021). Prediction of Distillation Column Temperature Using Machine Learning and Data Preprocessing. Korean Chemical Engineering Research, 59(2), 191-199. https://doi.org/10.9713/KCER.2021.59.2.191
  26. Lee, Y. (2022). Long and Short Term Prediction of Rebar Price Using Deep learning and Related Techniques, Ph.D. Dissertation, Konkuk University.
  27. Polson, N., & Sokolov, V. (2017). Deep learning forshort-term traffic flow prediction, Transportation Research, 79, 1-17.
  28. Schuster, M., & Paliwal, K. (1997). Bidirectional recurrent neural networks, IEEE transactions on Signal Processing, 45(11), 2673-2681. https://doi.org/10.1109/78.650093
  29. Scikit-learn (2022). https://scikit-learn.org/stable/modules/classes.html, accessed Jan 17, 2022.
  30. Taieb, S., Sorjamaa, A., & Bontempi, G. (2010). Multiple-output modeling for multi-step-ahead time series forecasting, Neurocomputing, 73(10-12), 1950-1957. https://doi.org/10.1016/j.neucom.2009.11.030
  31. Willmott, C. J., & Matsuura, K. (2005). Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance, Climate research, 30(1), 79-82. https://doi.org/10.3354/cr030079
  32. Yadav, S., & Shukla, S. (2016). Analysis of k-fold cross-validation over hold-out validation on colossal datasets for quality classification, International conference on advanced computing, IEEE, 78-83.