Name
Abstract | ||
|---|---|---|
Several empirical results on time series indicate that combining forecasts is, on average, better than selecting a single winning forecasting model. The success of the combination approach depends on how well the combination weights can be determined. Focusing on convex combinations – linear combinations with forecast weights constrained to be non-negative and to sum to unity – this paper proposes a new weight generation framework called Neural Expert Weighting (NEW). The framework generates dynamic weighting models based on neural networks, both relaxing in-sample performance dependence and abstracting statistical complexity. Assessed with 15 time series divided into two case studies – petroleum products and NN3 forecasting competition – the NEW models presented promising results. |
Year | DOI | Venue |
|---|---|---|
2015 | 10.1016/j.eswa.2015.07.017 | Expert Systems with Applications |
Keywords | Field | DocType |
Forecast combination,Convex combinations,Time series,Neural networks | Linear combination,Data mining,Weighting,Computer science,Regular polygon,Artificial intelligence,Artificial neural network,Machine learning | Journal |
Volume | Issue | ISSN |
42 | 22 | 0957-4174 |
Citations | PageRank | References |
0 | 0.34 | 11 |
Authors | ||
2 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Rafael de O. Valle dos Santos | 1 | 0 | 0.34 |
| Marley B. R. Vellasco | 2 | 280 | 47.47 |