Emerging Trend of Transaction and Investment: Bitcoin Price Prediction using Machine Learning

Abstract

Bitcoin is the most popular cryptocurrency with the highest market value. It was said to have potential in changing the way of trading in future. However, Bitcoin price prediction is a hard task and difficult for investors to make a decision. This is caused by nonlinearity property of the Bitcoin price. Hence, a better forecasting method is essential to minimize the risk from inaccuracy decision. The aim of this paper is to first compare three different neural networks which are Feedforward Neural Network (FNN), Nonlinear Autoregressive with Exogenous Input (NARX) Neural Network and Nonlinear Autoregressive (NAR) Neural Network by obtaining the predicted result for each model. The best model is identified by evaluating the performance measurement of each model. After obtaining the best model, it is used to undergo 30 days ahead forecast. The result showed that the performance of NARX out-performed FNN and NAR. It is proven NARX is the suitable neural network to forecast Bitcoin price. The resulting model provides new insights into Bitcoin forecasting using NARX which directly benefits the investors and economists in lowering the risk of making the inaccurate decision when it comes to investing in Bitcoin.