Abstract
Bitcoin is a current popular cryptocurrency with a promising future. It’s like a stock market with time series, the series of indexed data points. We looked at different deep learning networks and methods of improving the accuracy, including min-max normalization, Adam optimizer and windows min-max normalization. We gathered data on the Bitcoin price per minute, and we rearranged them to reflect Bitcoin price in hours, a total of 56,832 points. We took 24 hours of data as input and output the Bitcoin price of the next hour. We compared the different models and found that the lack of memory means that Multi-Layer Perceptron (MLP) is ill-suited for the case of predicting price based on current trend. Long Short-Term Memory (LSTM) provides relatively the best prediction when past memory and Gated Recurrent Network (GRU) is included in the model.
Highlights
Bitcoin is a cryptocurrency and a form of electronic cash
We looked at different deep learning networks and methods of improving the accuracy, including min-max normalization, Adam optimizer and windows min-max normalization
We compared the different models and found that the lack of memory means that Multi-Layer Perceptron (MLP) is ill-suited for the case of predicting price based on current trend
Summary
It is a digital currency that can be sent from user to user on the peer-to-peer Bitcoin network without intermediaries. It keeps a record of trading among peers and every record is encrypted. Greaves and Au used linear regression, logistic regression and support vector machine to predict Bitcoin future price with low performance [1]. His research sheds light on Bitcoin prediction which is similar to stock price. Madan et al used more machine learning approaches like generalized linear models and random forest to address Bitcoin prediction problem [4]. Researches mentioned above focuses on predicting the Bitcoin price of the day. Multiple Layer Perceptron (MLP), Long-ShortTerm-Memory (LSTM) and Gated recurrent units (GRU) models are compared on the test dataset with cross-validation
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have