KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction of Cryptocurrency Price Trend Using Gradient Boosting

그래디언트 부스팅을 활용한 암호화폐 가격동향 예측

  • 허주성 (한국기술교육대학교 컴퓨터공학부) ;
  • 권도형 (한국기술교육대학교 창의융합공학협동과정 ICT융합) ;
  • 김주봉 (한국기술교육대학교 컴퓨터공학부) ;
  • 한연희 (한국기술교육대학교 컴퓨터공학부) ;
  • 안채헌 (한국기술교육대학교 메카트로닉스공학부)
  • Received : 2018.07.13
  • Accepted : 2018.08.20
  • Published : 2018.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Stock price prediction has been a difficult problem to solve. There have been many studies to predict stock price scientifically, but it is still impossible to predict the exact price. Recently, a variety of types of cryptocurrency has been developed, beginning with Bitcoin, which is technically implemented as the concept of distributed ledger. Various approaches have been attempted to predict the price of cryptocurrency. Especially, it is various from attempts to stock prediction techniques in traditional stock market, to attempts to apply deep learning and reinforcement learning. Since the market for cryptocurrency has many new features that are not present in the existing traditional stock market, there is a growing demand for new analytical techniques suitable for the cryptocurrency market. In this study, we first collect and process seven cryptocurrency price data through Bithumb's API. Then, we use the gradient boosting model, which is a data-driven learning based machine learning model, and let the model learn the price data change of cryptocurrency. We also find the most optimal model parameters in the verification step, and finally evaluate the prediction performance of the cryptocurrency price trends.

과거부터 주식시장의 주가 예측은 풀리지 않는 난제이다. 이를 과학적으로 예측하기 위해 다양한 시도 및 연구들이 있어왔지만 정확한 가격을 예측하는 것은 불가능하다. 최근 분산 원장이라는 개념을 기술적으로 구현한 최초의 암호화폐인 비트코인을 시작으로 다양한 종류의 암호화폐가 개발되면서 암호화폐 시장이 형성되었고, 그 가격을 예측하기 위해 다양한 접근들이 시도되고 있다. 특히, 기존의 전통적인 주식시장에서의 주가 예측 기법들을 적용하려는 시도부터 딥러닝과 강화학습을 적용하려는 시도까지 다양하다. 하지만 암호화폐 시장은 기존 주식 시장에는 없던 여러 가지 새로운 특징을 가지는 시장으로서 전통적인 주식 시장 분석 기술뿐만 아니라 암호화폐 시장에 적합한 새로운 분석 기술에 관한 수요가 증가하고 있는 상황이다. 본 연구에서는 우선 빗썸의 API를 통하여 7개의 암호화폐 가격 데이터를 수집 및 가공하였다. 이후, Data-Driven 방식의 지도학습 기반 기계학습 모델인 그래디언트 부스팅 모델을 채택하여 암호화폐 가격 데이터 변화를 학습하고, 검증단계에서 가장 최적의 모델 파라미터를 산출하고, 최종적으로 테스트 데이터를 활용하여 암호화폐 가격동향 예측 성능을 평가한다.

Keywords

References

  1. M. S. Helen, C. Chester, A. Adam, K. Y. Dror, S. Eugene, and P. Tobias, "Quantifying Wikipedia Usage Patterns Before Stock Market Moves," Scientific Reports, May 2013.
  2. S. Nakamoto, "Bitcoin: A Peer-to-Peer Electronic Cash System," [Internet], http://www.bitcoin.org, 2008.
  3. R. Phillips and D. Gorse, "Predicting Cryptocurrency Price Bubbles Using Social Media Data and Epidemic Modelling," IEEE Symposium Series on Computational Intelligence, 2017.
  4. A. Radityo, Q. Munajat, and I. Budi, "Prediction of Bitcoin exchange rate to American dollar using artificial neural network methods," International Conference on Advanced Computer Science and Information Systems, 2017.
  5. Z. Jiang and J. Liang, "Cryptocurrency portfolio management with deep reinforcement learning," Intelligent Systems Conference, 2017.
  6. L. Li, Y. Wu, Y. Ou, Q. Li, Y. Zhou, and D. Chen, "Research on machine learning algorithms and feature extraction for time series," The 28th IEEE Annual International Symposium on Personal, Indoor, and Mobile Radio Communications (PIMRC), Oct. 2017.
  7. J. W. Lee, "A Stock Trading System based on Supervised Learning of Highly Volatile Stock Price Patterns," Journal of KIISE : Computing Practices and Letters, Vol.19 No.1, pp.23-29, 2013.
  8. Y. Song, J. W. Lee, and J. Lee, "Performance Evaluation of Price-based Input Features in Stock Price Prediction using Tensorflow," KIISE Transactions on Computing Practices, Vol.23, No.11, pp.625-631, 2018.
  9. Y. Kim, E. Shin, and T. Hong, "Comparison of Stock Price Index Prediction Performance Using Neural Networks and Support Vector Machine," The Journal of Internet Electronic Commerce Resarch, Vol.4, No.3, pp.221-243, 2004.
  10. A. M. Ho and R. M. Hyun, "Algorithm trading system development using machine learning," Hanbit Media(Inc), Apr. 2016, ISBN: 9788968488030.
  11. Bithumb [Internet], https://www.bithumb.com/
  12. T. Yook, "Change of Financial Systems by Virtual Currency or Cryptocurrency and its Legal Implications," Kangwon Law Review, Vol.53, pp.225-270, 2018. https://doi.org/10.18215/kwlr.2018.53..225
  13. Y. Song and J. Lee, "A Design and Implementation of Deep Learning Model for Stock Predictions using TensorFlow," Processing of Korea Information Science Society Conference, pp.799-801, June 2017.
  14. Y. Dai and Y. Zhang, "Machine Learning in Stock Price Trend Forecasting," Stanford University, 2013.
  15. J. W. Lee and J. M. O, "Artificial Intelligence: Integrated Multiple Simulation for Optimizing Performance of Stock Trading Systems based on Neural Networks," KIPS Journal B (2001-2012), Vol.14B, No.2, pp.127-134, Feb. 2007.
  16. Z. Jiang, D. Xu, and J. Liang, "A Deep Reinforcement Learning Framework for the Financial Portfolio Management Problem," Journal of Machine Learning Research, arXiv:1706.10059v2, 2017.
  17. I.-S. Baek, "Local Hurst Exponent Indicator to Sell the Abruptly Rising Stock," Korean Association of Financial Engineering, Vol.9, No.3, pp.149-165, Sept. 2010.
  18. S. Cho and J.-S. Choi, "A Monte Carlo Experiment on the Power of Augmented Dickey-Fuller Unit Root Test," Journal of The Korean Official Statistics, Vol.10, No.1, 2005.
  19. D.-H. Kwon, J.-S. Heo, J.-B. Kim, H.-K. Lim, and Y.-H. Han, "Correlation Analysis and Regression Test on Cryptocurrency Price Data," Proceedings of Spring Korea Information Processing Society Conference, May 2018.
  20. P. Hall, B. U. Park, and R. J. Samworth, "Choice of Neighbor Order in Nearest-neighbor Classification," Annals of Statistics, Vol.36, No.5, pp.2135-2152, 2008. https://doi.org/10.1214/07-AOS537
  21. C. J. C. Burges, "A Tutorial on Support Vector Machines for Pattern Recognition," Data Mining and Knowledge Discovery, Vol.2, No.2, pp.121-167, Jun. 1998. https://doi.org/10.1023/A:1009715923555
  22. Y. D. Kim, K. H. Kim, and S. H. Song, "Comparison of Boosting and SVM," Journal of the Korean Data And Information Science Sociaty, Vol.16, No.4, pp.999-1012, 2005.
  23. J. H. Jung and D. K. Min, "The study of foreign exchange trading revenue model using decision tree and gradient boosting," Journal of the Korean Data And Information Science Society, Vol.24, No.1, pp.161-170, 2013. https://doi.org/10.7465/jkdi.2013.24.1.161
  24. Alexey Natekin and Alois Knoll "Gradient Boosting Machines, a Tutorial," Front Neurorobot, Vol.7, No.21, 2013.
  25. S. Kar, S. Saha, L. Khaidem, and S. R. Dey, "Predicting the Direction of Stock Market Price Using Tree Based Classifiers," Elsevier North American Journal of Economics and Finance, Jul. 2018. (available online).
  26. B. Gorman, "A Kaggle Master Explains Gradient Boosting," [Internet], http://blog.kaggle.com/2017/01/23/a-kaggle-master-explains-gradient-boosting, Jan 2017.
  27. J. Bergstra and Y. Bengio. "Random search for hyper-parameter optimization," Journal of Machine Learning Research, Vol.13 pp.281-305, 2012.
  28. T. Fushiki, "Estimation of prediction error by using K-fold cross-validation," Statistics and Computing, Vol.21, No.2, pp.137-146, 2011. https://doi.org/10.1007/s11222-009-9153-8
  29. DASK: Scalable analytics in Python [Internet], https://dask.pydata.org/