Data-Driven Bitcoin Price Prediction Using Advanced Machine Learning

Abstract

          Bitcoin uses a peer-to-peer technology to operate with no central authority or banks. Bitcoin is  open-source;  its  design  is  public,  nobody  owns  or   controls  Bitcoin and  everyone  can  take part. Digital currency bring into use as open source software in  2009 by pseudonymous creator Satoshi Nakamoto It  is  a  cryptocurrency,  so-called  because  it  uses  cryptography to control the  creation and  transfer of  money. The goal of this work is to compare the accuracy of bitcoin price in USD prediction based on Long Short-term Memory (LSTM) network with self-attention. Real-time price data is collected by Pycurl from Bitfine. LSTM model is implemented by Keras and TensorFlow. The proposed model used in this work is mainly to present a classical comparison of time series forecasting, as expected, it could make efficient prediction limited in short-time interval, and the outcome depends on the time period. The LSTM could reach a better performance, with extra, indispensable time for model training, especially via CPU.