TY - JOUR
T1 - Univariate and Multivariate Machine Learning Forecasting Models on the Price Returns of Cryptocurrencies
AU - Miller, Dante
AU - Kim, Jong Min
N1 - Publisher Copyright:
© 2021 by the authors.
PY - 2021/10
Y1 - 2021/10
N2 - In this study, we predicted the log returns of the top 10 cryptocurrencies based on market cap, using univariate and multivariate machine learning methods such as recurrent neural networks, deep learning neural networks, Holt’s exponential smoothing, autoregressive integrated moving average, ForecastX, and long short-term memory networks. The multivariate long short-term memory networks performed better than the univariate machine learning methods in terms of the prediction error measures.
AB - In this study, we predicted the log returns of the top 10 cryptocurrencies based on market cap, using univariate and multivariate machine learning methods such as recurrent neural networks, deep learning neural networks, Holt’s exponential smoothing, autoregressive integrated moving average, ForecastX, and long short-term memory networks. The multivariate long short-term memory networks performed better than the univariate machine learning methods in terms of the prediction error measures.
KW - cryptocurrencies
KW - deep learning networks
KW - long short-term memory networks
KW - recurrent neural networks
UR - https://www.scopus.com/pages/publications/85130483699
UR - https://www.scopus.com/pages/publications/85130483699#tab=citedBy
U2 - 10.3390/jrfm14100486
DO - 10.3390/jrfm14100486
M3 - Article
AN - SCOPUS:85130483699
SN - 1911-8066
VL - 14
JO - Journal of Risk and Financial Management
JF - Journal of Risk and Financial Management
IS - 10
M1 - 486
ER -