A Comparative Study of Bitcoin Price Prediction Using Deep Learning

Abstract

Bitcoin has recently received a lot of attention from the media and the public due to its recent price surge and crash. Correspondingly, many researchers have investigated various factors that affect the Bitcoin price and the patterns behind its fluctuations, in particular, using various machine learning methods. In this paper, we study and compare various state-of-the-art deep learning methods such as a deep neural network (DNN), a long short-term memory (LSTM) model, a convolutional neural network, a deep residual network, and their combinations for Bitcoin price prediction. Experimental results showed that although LSTM-based prediction models slightly outperformed the other prediction models for Bitcoin price prediction (regression), DNN-based models performed the best for price ups and downs prediction (classification). In addition, a simple profitability analysis showed that classification models were more effective than regression models for algorithmic trading. Overall, the performances of the proposed deep learning-based prediction models were comparable.

Cryptocurrencies and Artificial Intelligence: Challenges and Opportunities

“…Simple linear time series models sometimes leave certain aspects of economic and financial data unexplained [29]. That is why some authors tested nonlinear time series models to model nonlinear behavior in economic and financial time series data [13], [14], [16], [20]- [28]. Table 2 shows a summary for the research on price prediction of cryptocurrencies comparing the used AI techniques and datasets in each paper.…”

“…Mean square error (MSE), root mean square error (RMSE) and mean absolute error (MAE) were used in [21], [25]. Mean absolute percentage error (MAPE) was used in [20], [22], [26]. Accuracy, recall, precision and F1 Score were used in [16], [20], [27].…”

“…Mean absolute percentage error (MAPE) was used in [20], [22], [26]. Accuracy, recall, precision and F1 Score were used in [16], [20], [27]. Moreover, the results can not be easily replicated due to the different models' parameters that are not thoroughly mentioned.…”

“…Deep learning was also used in [28] to predict Bitcoin and Ethereum prices in Australian dollars (AUD). A comparative study of different deep learning models (deep neural network (DNN), long-short term memory (LSTM) and artificial neural network (ANN)) was done in [20] for Bitcoin price prediction. LSTM-based prediction models slightly outperformed other techniques for regression of Bitcoin price while DNN-based models performed better for classification of price changes whether up or down.…”

Investigation of Dual-Flow Deep Learning Models LSTM-FCN and GRU-FCN Efficiency against Single-Flow CNN Models for the Host-Based Intrusion and Malware Detection Task on Univariate Times Series Data

“…The maximum achieved accuracy was equal to 94.5% and 99.3% for 100 and 1000 first system calls, respectively, with a simple CNN configuration [14]. In recent years, research on the combination of CNNs and RNNs into one model has shown promising results [72][73][74] and was applied from image recognition to Bitcoin price prediction tasks. This encouraged many researchers to apply similar methods in the IDS research field.…”