Time Series Classification of Cryptocurrency Price Trend Based on a Recurrent LSTM Neural Network
0
조회
0
다운로드
4
인용
0
참고문헌
키워드
초록
In this study, we applied the long short-term memory (LSTM) model to classify the cryptocurrency price timeseries. We collected historic cryptocurrency price time series data and preprocessed them in order to makethem clean for use as train and target data. After such preprocessing, the price time series data weresystematically encoded into the three-dimensional price tensor representing the past price changes ofcryptocurrencies. We also presented our LSTM model structure as well as how to use such price tensor as inputdata of the LSTM model. In particular, a grid search-based k-fold cross-validation technique was applied to findthe most suitable LSTM model parameters. Lastly, through the comparison of the f1-score values, our studyshowed that the LSTM model outperforms the gradient boosting model, a general machine learning modelknown to have relatively good prediction performance, for the time series classification of the cryptocurrencyprice trend. With the LSTM model, we got a performance improvement of about 7% compared to using the GBmodel.
Abstract
In this study, we applied the long short-term memory (LSTM) model to classify the cryptocurrency price timeseries. We collected historic cryptocurrency price time series data and preprocessed them in order to makethem clean for use as train and target data. After such preprocessing, the price time series data weresystematically encoded into the three-dimensional price tensor representing the past price changes ofcryptocurrencies. We also presented our LSTM model structure as well as how to use such price tensor as inputdata of the LSTM model. In particular, a grid search-based k-fold cross-validation technique was applied to findthe most suitable LSTM model parameters. Lastly, through the comparison of the f1-score values, our studyshowed that the LSTM model outperforms the gradient boosting model, a general machine learning modelknown to have relatively good prediction performance, for the time series classification of the cryptocurrencyprice trend. With the LSTM model, we got a performance improvement of about 7% compared to using the GBmodel.
참고문헌 (18)
- W. M. Grove, "Clinical versus mechanical prediction : a meta-analysis", Psychological Assessment, 12(1), pp.19~30 (2000)
- E. Kita, "Application of Bayesian network to stock price prediction", Artificial Intelligence Research, 1(2), pp.171~184 (2012)
- Giang-Truong Nguyen, "A Survey about Consensus Algorithms Used in Blockchain", JIPS(Journal of Information Processing Systems), 14(1), pp.101~128 (2018), 한국정보처리학회[DOI]
- Pradip Kumar Sharma, "Block-VN: A Distributed Blockchain Based Vehicular Network Architecture in Smart City", JIPS(Journal of Information Processing Systems), 13(1), pp.184~195 (2017), 한국정보처리학회[DOI]
- "Bitcoin: a peer-to-peer electronic cash system" (2008)[URL]
- Ubaidullah Rajput, "A Solution towards Eliminating Transaction Malleability in Bitcoin", JIPS(Journal of Information Processing Systems), 14(4), pp.837~850 (2018), 한국정보처리학회[DOI]
- H. Jang, "An empirical study on modeling and prediction of bitcoin prices with Bayesian neural networks based on blockchain information", IEEE Access, 6, pp.5427~5437 (2017)
- "Deep learning for time-series analysis" (2017)[URL]
- Y. B. Kim, "Predicting fluctuations in cryptocurrency transactions based on user comments and replies", PloS One, 11(8) (2016)
- "A deep reinforcement learning framework for the financial portfolio management problem" (2017)[URL]
- A. Radityo, "Prediction of bitcoin exchange rate to American dollar using artificial neural network methods", Proceedings of 2017 International Conference on Advanced Computer Science and Information Systems (ICACSIS), pp.433~438 (2017)
- 허주성, "그래디언트 부스팅을 활용한 암호화폐 가격동향 예측", 정보처리학회 논문지, 7(10), pp.387~396 (2018), 한국정보처리학회[DOI]
- S. Hochreiter, "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)
- H. Larochelle, "An empirical evaluation of deep architectures on problems with many factors of variation", Proceedings of the 24th International Conference on Machine Learning, pp.473~480 (2007)
- R. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection", Proceedings of the 14th International Joint Conference on Artificial Intelligence, pp.1137~1145 (1995)
- T. Fushiki, "Estimation of prediction error by using K-fold cross-validation", Statistics and Computing, 21(2), pp.137~146 (2011)
- A. Natekin, "Gradient boosting machines, a tutorial", Frontiers in Neurorobotics, 7 (2013)
- D. M. W. Powers, "Evaluation : from precision, recall and F-measure to ROC, informedness, markedness and correlation", Journal of Machine Learning Technologies, 2(1), pp.37~63 (2011)