Research Article
Daily Crude Oil Price Forecasting Using Hybridizing Wavelet and Artificial Neural Network Model
Table 1
Training and testing performance of different network architecture of ANN model.
| Data | Network architecture | Training | Testing | Input | Hidden | RMSE | MAPE | RMSE | MAPE |
| Brent
| 1 | 1 | 0.7281 | 2.28% | 0.9932 | 1.65% | 2 | 4 | 0.5023 | 1.60% | 0.9910 | 1.64% | 3 | 2 | 0.5108 | 1.60% | 0.9912 | 1.64% | 4 | 2 | 0.5059 | 1.60% | 0.9910 | 1.64% | 5 | 1 | 0.5244 | 1.61% | 0.9928 | 1.65% | 6 | 1 | 0.5231 | 1.61% | 0.9920 | 1.65% |
| WTI | 1 | 3 | 0.5651 | 1.72% | 0.9507 | 1.79% | 2 | 4 | 0.5590 | 1.72% | 0.9452 | 1.79% | 3 | 5 | 0.5187 | 1.69% | 0.9496 | 1.79% | 4 | 7 | 0.5137 | 1.67% | 0.9514 | 1.80% | 5 | 1 | 0.5626 | 1.72% | 0.9529 | 1.80% | 6 | 1 | 0.5636 | 1.72% | 0.9493 | 1.79% |
|
|