GJR-GARCH Volatility Modeling under NIG and ANN for Predicting Top Cryptocurrencies

Cryptocurrencies are currently traded worldwide, with hundreds of different currencies in existence and even more on the way. This study implements some statistical machine learning approaches for cryptocurrency investments. First, we implement GJR-GARCH over GARCH model to estimate volatility ten popular cryptocurrencies based market capitalization: Bitcoin, Bitcoin Cash, SV, Chainlink, EOS, Ethereum, Litecoin, TETHER, Tezos, XRP. Then, use Monte Carlo simulations generate conditional variance using model, calculate value at risk (VaR) simulations. We also tail-risk VaR backtesting. Finally, an artificial neural network (ANN) predicting prices cryptocurrencies. The graphical analysis mean square errors (MSEs) from ANN models confirmed that predicted close prices. For cryptocurrencies, perform better than traditional ARIMA models.