한국융합학회논문지 (Journal of the Korea Convergence Society)

  • 제13권4호
  • /
  • Pages.17-24
  • /
  • 2022
  • /
  • 2233-4890(pISSN)
  • /
  • 2713-6353(eISSN)
한국융합학회 (Korea Convergence Society)
권호 표지
DOI QR코드

DOI QR Code

비트코인 가격 예측을 위한 LSTM 모델의 Hyper-parameter 최적화 연구

A Study on the Hyper-parameter Optimization of Bitcoin Price Prediction LSTM Model

  • Kim, Jun-Ho (Department of Game Design and Develpment, Sangmyung University) ;
  • Sung, Hanul (Department of Game Design and Develpment, Sangmyung University)
  • 투고 : 2022.01.13
  • 심사 : 2022.04.20
  • 발행 : 2022.04.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

비트코인은 정부나 금융기관에 의존되어 있지 않은 전자 거래를 지향하며 만들어진 peer-to-peer 방식의 암호화폐이다. 비트코인은 최초 발행 이후 거대한 블록체인 금융 시장을 생성했고, 이에 따라 기계 학습을 이용한 비트코인 가격 데이터를 예측하는 연구들이 활발해졌다. 그러나 기계 학습 연구의 비효율적인 Hyper-parameter 최적화 과정이 연구 진행에 있어 비용적인 측면을 악화시키고 있다. 본 논문은 LSTM(Long Short-Term Memory) 층을 사용하는 비트코인 가격 예측 모델에서 가장 대표적인 Hyper-parameter 중 Timesteps, LSTM 유닛의 수, 그리고 Dropout 비율의 전체 조합을 구성하고 각각의 조합에 대한 예측 성능을 측정하는 실험을 통해 정확한 비트코인 가격 예측을 위한 Hyper-parameter 최적화의 방향성을 분석하고 제시한다.

Bitcoin is a peer-to-peer cryptocurrency designed for electronic transactions that do not depend on the government or financial institutions. Since Bitcoin was first issued, a huge blockchain financial market has been created, and as a result, research to predict Bitcoin price data using machine learning has been increasing. However, the inefficient Hyper-parameter optimization process of machine learning research is interrupting the progress of the research. In this paper, we analyzes and presents the direction of Hyper-parameter optimization through experiments that compose the entire combination of the Timesteps, the number of LSTM units, and the Dropout ratio among the most representative Hyper-parameter and measure the predictive performance for each combination based on Bitcoin price prediction model using LSTM layer.

키워드

참고문헌

  1. https://www.binance.com
  2. S. W. Kim. (2021). Performance Analysis of Bitcoin Investment Strategy using Deep Learning. Journal of the Korea Convergence Society, 12(4), 249-258. https://doi.org/10.15207/JKCS.2021.12.4.249
  3. J. G. Won & T. H. Hong. (2021). The Prediction of Cryptocurrency on Using Text Mining and Deep Learning Techniques : Comparison of Korean and USA Market. Knowledge Management Research, 22(2), 1-17.
  4. S. McNally, J. Roche & S. Caton. (2018). Predicting the Price of Bitcoin Using Machine Learning. 26th Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, 339-343.
  5. I. T. Joo & S. H. Choi. (2018). Stock Prediction Model based on Bidirectional LSTM Recurrent Neural Network. Journal of Korea Institute of Information, Electronics, and Communication Technology 11(2), 204-208. https://doi.org/10.17661/JKIIECT.2018.11.2.204
  6. K. J. Jeong & J. S. Choi. (2015). Deep Recurrent Neural Network. Communications of the Korean Institute of Information Scientists and Engineers, 33(8), 39-43.
  7. T. Yu & H. Zhu. (2020). Hyper-Parameter Optimization: A Review of Algorithms and Applications.
  8. S. H. Ji, U. J. Baek, M. G. Shin, Y. H. Goo, S. H. Yoon & M. S. Kim. (2019). Design of LSTM Model for Prediction of Number of Bitcoin Transactions. Proceedings of Symposium of the Korean Institute of communications and Information Sciences, 472-473.
  9. D. H. Kown, J. S. Heo, J. B. Kim, H. K. Lim & Y. H. Han (2018). Correlation Analysis and Regression Test on Cryptocurrency Price Data. Proceedings of the Korea Information Processing Society Conference, 346-349.
  10. E. M. Kim & J. W. Hong. (2021). The Prediction model of cryptocurrency price using news sentiment analysis and deep learning. Knowledge Management Review, 22(2), 19-32. https://doi.org/10.15813/KMR.2021.22.2.002
  11. M. G. Gang, B. S. Kim & H. J. Shin. (2021). Machine Learning based Prediction of Bitcoin Price Fluctuation Using News Data. Korean Network Operations and Management Conference, 38-39.
  12. S. H. Ji, U. J. Baek, M. G. Shin, J. S. Park & M. S. Kim. (2019). A Study on the Prediction of Number of Bitcoin Network Transactions Based on Machine Learning. Korean Network Operations and Management Review, 22(1), 68-76.
  13. M. G. Gang, B. S. Kim, M. G. Shin, U. J. Baek & M. S. Kim. (2020). LSTM-based Prediction of Bitcoin Price Fluctuation using Sentiment Analysis. The Fall Conference of The Korean Institute of Communications and Information Sciences Conference, 1-2.
  14. J. Bergstra & Y. Bengio. (2012). Random search for hyper-parameter optimization. Journal of Machine Learning Resarch, 13(2).
  15. Y. U. Choi, D. U. Yoon, J. H. Choi & J. M. Byun. (2020). Hyperparameter Search for Facies Classification with Bayesian Optimization. Geophysics and Geophysical Exploration, 23(3), 157-167. https://doi.org/10.7582/GGE.2020.23.3.00157
  16. G. Sui, Y. Yu. (2020). Bayesian Contextual Bandits for Hyper Parameter Optimization. IEEE Access, 8, 42971-42979. https://doi.org/10.1109/access.2020.2977129
  17. https://upbit.com