Research Article
Integrated Feature Selection of ARIMA with Computational Intelligence Approaches for Food Crop Price Prediction
Table 5
The results of ARIMA-MARS for rice price forecasting.
| Variable selection results | BF | Coefficient | Variable | Relative importance (%) |
| Intercept | | | −13.404 | | 100.0 | BF1 = Max (0, Zt−13 + 35) | 0.407 | | 45.4 | BF2 = Max (0, Zt−7 − 0) | 23.543 | BF3 = Max (0, Zt−7 + 1.30) | −73.468 | BF4 = Max (0, Zt−7 + 1.87) | 49.716 | | 28.5 | BF5 = Max (0, −39.85 − Zt−1) | 0.479 |
|
|