Heuristic fine-tuning process

The initial sales forecasts from the HS-ELM-based NNs with different numbers of hidden neurons are transferred to the heuristic fine-tuning process. The initial forecasts can be umeasonable because the NN may be oveifitted. Let PN denote the set of percent changes of two neighboring values in a same-period sales data series Sj, and pf denote the percent change of the forecast of the series S. to its latest same-period observation. The initial forecast is considered unreasonable if one of the following conditions is met ... 

This section presents an in-depth discussion on the forecasting performance of the proposed HI model. The forecasting performance of the proposed HI model is first analyzed based on the experimental results presented in Section 9.4. Further analysis is then conducted to validate the superiority of the proposed model over other models based on public benchmark data sets. The effectiveness of the model s components, including the heuristic fine-tuning process, data preprocessing component and HI forecaster, is also analyzed in this section. 

---