Artificial Neural Networks for Realized Volatility Prediction in Cryptocurrency Time Series
Artificial Neural Networks for Realized Volatility Prediction in Cryptocurrency Time Series
R. Miura,L. Pichl,T. Kaizoji
2019 · DOI: 10.1007/978-3-030-22796-8_18
International Symposium on Neural Networks · 28 Citations
TLDR
It is shown that Ridge Regression performs the best, which supports the auto-regressive dynamics postulated by HARRV model, and can be used for dynamic risk hedging in algorithmic trading at cryptocurrency markets.