Forecasting the price of Bitcoin using deep learning

After constructing a feature system with 40 determinants that affect the price of Bitcoin considering aspects of the cryptocurrency market, public attention, and the macroeconomic environment, a deep learning method named stacked denoising autoencoders (SDAE) is utilized to predict the price of Bitcoin. The results show that compared with the most popular machine learning methods, such as back propagation neural network (BPNN) and support vector regression (SVR) methods, the SDAE model performs better in both directional and level prediction, measured using commonly used indicators, i.e., mean absolute percentage error (MAPE), root mean squared error (RMSE), and directional accuracy (DA).

Automated summary

After constructing a feature system with 40 determinants affecting the price of Bitcoin, a deep learning method called SDAE was used for prediction. The SDAE model outperformed traditional methods such as BPNN and SVR in both directional and level prediction accuracy.