Research Article
Prediction of Currency Volume Issued in Taiwan Using a Hybrid Artificial Neural Network and Multiple Regression Approach
Table 11
Improvement of the proposed models in comparison with the single-stage models.
| Models | MAPE (%) | RMSE (%) | MAD (%) |
| Proposed hybrid MRVIF-ANN model | | | | ARIMA | 36.52 | 5.88 | 33.24 | ANN | 36.21 | 14.61 | 34.03 | MRSIG | 17.73 | 87.19 | 88.03 | MRSEL | 15.39 | 87.26 | 88.10 | Proposed hybrid MRSIG-ANN model | | | | ARIMA | 37.35 | 7.73 | 34.26 | ANN | 37.04 | 16.29 | 35.04 | MRSIG | 18.81 | 87.44 | 88.21 | MRSEL | 16.49 | 87.51 | 88.28 | Proposed hybrid MRSEL-ANN model | | | | ARIMA | 37.80 | 6.99 | 34.76 | ANN | 37.50 | 15.62 | 35.52 | MRSIG | 19.39 | 87.34 | 88.30 | MRSEL | 17.09 | 87.41 | 88.37 |
|
|