Skip to main content
Fig. 6 | Applied Network Science

Fig. 6

From: Using correlated stochastic differential equations to forecast cryptocurrency rates and social media activities

Fig. 6

Each subfigure shows 14 days of prediction compared to the ground truth with the previous 14 days of ground truth as reference. (a, b) shows the prediction at the end of April 2017. (c, d) shows the prediction at the end of June 2017. (e, f) shows the predictions at the end of August 2017. (a, c, e) shows the predictions for Bitcoin at the corresponding time ranges and (b, d, f) for Ethereum. Mape values for each subfigure can be seen in TableĀ 2. Estimated parameters and correlations for these examples can be seen in Table 5 (Appendix 4)

Back to article page