Research Article
Is Deep Learning for Image Recognition Applicable to Stock Market Prediction?
Table 4
Accuracy comparison for CNNs with different loss functions during the test period.
| ā | Loss function | Hit ratio | Specificity | Sensitivity |
| CNN1 | MSE | 0.66 | 0.6611 | 0.6508 | CEE | 0.65 | 0.9596 | 0.3810 |
| CNN2 | MSE | 0.67 | 0.6825 | 0.6209 | CEE | 0.56 | 0.5248 | 0.6144 |
| CNN3 | MSE | 0.62 | 0.6151 | 0.6302 | CEE | 0.60 | 0.6429 | 0.4840 |
| CNN4 | MSE | 0.62 | 0.6114 | 0.6393 | CEE | 0.58 | 0.5939 | 0.5868 |
|
|