Cryptocurrencies chaotic co-movement forecasting with neural networks

In this study Non-Linear forecasting models have been implemented to forecast the seven major cryptocurrencies. To the best of the authors knowledge, this is the first study to forecast the cryptocurrencies chaotic co-movement forecasting using non-linear models like Neural networks. The study finds that LSTM yields better result for lags 0 and 0-3 and for large lags 0-7, the ANN is the best. Further study confirms that predictions using variables like volume is not suitable for forecasting in any case. The findings of the study will impact Policy makers and investors.