JIPS (Çѱ¹Á¤º¸Ã³¸®ÇÐȸ)
Current Result Document :
ÇѱÛÁ¦¸ñ(Korean Title) |
Time Series Classification of Cryptocurrency Price Trend Based on a Recurrent LSTM Neural Network |
¿µ¹®Á¦¸ñ(English Title) |
Time Series Classification of Cryptocurrency Price Trend Based on a Recurrent LSTM Neural Network |
ÀúÀÚ(Author) |
Do-Hyung Kwon
Ju-Bong Kim
Ju-Sung Heo
Chan-Myung Kim
Youn-Hee Han
|
¿ø¹®¼ö·Ïó(Citation) |
VOL 15 NO. 03 PP. 0694 ~ 0706 (2019. 06) |
Çѱ۳»¿ë (Korean Abstract) |
|
¿µ¹®³»¿ë (English Abstract) |
In this study, we applied the long short-term memory (LSTM) model to classify the cryptocurrency price time series. We collected historic cryptocurrency price time series data and preprocessed them in order to make them clean for use as train and target data. After such preprocessing, the price time series data were systematically encoded into the three-dimensional price tensor representing the past price changes of cryptocurrencies. We also presented our LSTM model structure as well as how to use such price tensor as input data of the LSTM model. In particular, a grid search-based k-fold cross-validation technique was applied to find the most suitable LSTM model parameters. Lastly, through the comparison of the f1-score values, our study showed that the LSTM model outperforms the gradient boosting model, a general machine learning model known to have relatively good prediction performance, for the time series classification of the cryptocurrency price trend. With the LSTM model, we got a performance improvement of about 7% compared to using the GB model.
|
Å°¿öµå(Keyword) |
Classification
Gradient Boosting
Long Short-Term Memory
Time Series Analysis
|
ÆÄÀÏ÷ºÎ |
PDF ´Ù¿î·Îµå
|