Predicting Crypto Currency Prices Using Neural Networks

Abstract— Crypto price prediction is a category of time series prediction which extremely challenging due to the dependence of crypto prices on several financial, socio-economic and political parameters etc. Moreover, small inaccuracies in crypto price predictions may result in huge losses to firms which use crypto price prediction results for financial analysis and investments. Off late, artificial intelligence and machine learning based techniques are being used widely for crypto price prediction due to relatively higher accuracy compared to conventional statistical techniques. The proposed work employs back propagation based training with Bayesian optimization, along with the data pre-processing using the discrete wavelet transform (DWT) for crypto price prediction. It has been shown that the proposed system attains lesser mean square percentage error compared to previously existing technique. Keywords—Crypto price Forecasting, Artificial Neural Network (ANN), Back Propagation, Discrete Wavelet Transform (DWT), Mean Absolute Percentage Error (MAPE).