Predicting the Price of Bitcoin Using Machine Learning
By Sean McNally, Jason Roche, Simon Caton. 2018
580 citations recorded by the source corpus.
The goal of this paper is to ascertain with what accuracy the direction of Bitcoin price in USD can be predicted. The price data is sourced from the Bitcoin Price Index. The task is achieved with varying degrees of success through the implementation of a Bayesian optimised recurrent neural network (RNN) and a Long Short Term Memory (LSTM) network. The LSTM achieves the highest classification accuracy of 52% and a RMSE of 8%. The popular ARIMA model for time series forecasting is implemented as a comparison to the deep learning models. As expected, the non-linear deep learning methods outperform the ARIMA forecast which performs poorly. Finally, both deep learning models are benchmarked on both a GPU and a CPU with the training time on the GPU outperforming the CPU implementation by 67.7%.
Subfields: Economics and Econometrics, Electrical and Electronic Engineering, Management Science and Operations Research, Time-Series & Forecasting
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Economics and Econometrics
- Omer Berat Sezer
- A. Ozbayoglu
- M. Ugur Gudelek
- Alexander Deinert
- Thomas G. Fischer
- Christopher Krauss
- David Martínez-Rego
- Carmine Ventre
In Electrical and Electronic Engineering
- A. Ozbayoglu
- M. Ugur Gudelek
- Omer Berat Sezer
- Christopher Krauss
- Jaewook Lee
- M. Omair Shafiq
- Jingyi Shen
- Huisu Jang
In Management Science and Operations Research
- Omer Berat Sezer
- A. Ozbayoglu
- M. Ugur Gudelek
- Alexander Deinert
- Weiwei Jiang
- Thomas G. Fischer
- Christopher Krauss
- David Martínez-Rego
In Time-Series & Forecasting
- M. Ugur Gudelek
- Omer Berat Sezer
- A. Ozbayoglu
- Christopher Krauss
- Thomas G. Fischer
- Jaewook Lee
- M. Omair Shafiq
- Jingyi Shen
Citations in the corpus
- Financial Time Series Forecasting with Deep Learning : A Systematic Literature Review: 2005-2019 (2019, methodology): “[182] Bitcoin 2013-2016 Price data 100d 30d Bayesian optimized RNN, LSTM Sensitivity, specificity, precision, accuracy, RMSE Keras, Python, Hyperas”
- Statistical Arbitrage in Cryptocurrency Markets (2019, background): “McNally et al. (2018) investigate the performance of state-of-the-art deep learning models, such as a long short-term memory (LSTM) network, in predicting future price changes of Bitcoin.”
- An Empirical Study on Modeling and Prediction of Bitcoin Prices With Bayesian Neural Networks Based on Blockchain Information (2018, methodology): “Reference [14] predicts the Bitcoin pricing process using machine learning techniques, such as recurrent neural networks (RNNs) and long short-term memory (LSTM), and compare results with those obtained using autoregressive integrated moving average (ARIMA) models.”
- Cryptocurrency trading: a comprehensive survey (2020, methodology): “sing GARCH models combined with gold and US dollars. From late 2016 to 2017, machine learning and deep learning technology were applied in prediction of cryptocurrency return. In 2016, McNally et al. [174] predicted Bitcoin price using LSTM algorithm. Bell and Zbikowski et al. [22,244] applied SVM a”
- Short-term stock market price trend prediction using a comprehensive deep learning system (2020, methodology): “in [27] leveraged RNN and LSTM on predicting the price of Bitcoin, optimized by using the Boruta algorithm for feature engineering part, and it works similarly to the random forest classifier.”
- A Comparison between ARIMA, LSTM, and GRU for Time Series Forecasting (2019, background): “[9] researched into the accuracy the track of Bitcoin price prediction in American dollars (USD).”
- An innovative neural network approach for stock market prediction (2018, methodology): “Sean used the recurrent neural network-LSTM, which was optimized by Bayesian, to predict the price of the coin, reaching 52% of accuracy [28].”