A multi-method forecasting algorithm: Linear unbiased estimation of combine forecast

This paper proposes a dynamic ensemble algorithm to combine forecasting results from multiple methodologies subject to their local (recent) predictive performance. In contrast to conventional combination forecasts, the proposed algorithm runs a sparsification process to merge a subset of methodology...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Knowledge-based systems Ročník 239; s. 107990
Hlavní autoři: Bekiroglu, Korkut, Gulay, Emrah, Duru, Okan
Médium: Journal Article
Jazyk:angličtina
Vydáno: Amsterdam Elsevier B.V 05.03.2022
Elsevier Science Ltd
Témata:
Algorithms
Bias
Combine forecasting
Crude oil prices
Forecasting
Methodology
Model learning
Performance prediction
Petroleum
Research methodology
Sparse model combination
Sparse model combination
Combine forecasting
Model learning
ISSN:0950-7051, 1872-7409
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:This paper proposes a dynamic ensemble algorithm to combine forecasting results from multiple methodologies subject to their local (recent) predictive performance. In contrast to conventional combination forecasts, the proposed algorithm runs a sparsification process to merge a subset of methodology space to avoid overfitting and improve out-of-sample accuracy. The methodology space consists of various linear and non-linear as well as univariate and multivariate forecasting algorithms frequently used in the literature and industrial practice. The proposed algorithm continuously searches for the best combination to learn models weight. The weights are then used to combine the next forecasting coming from all forecasters. Two empirical studies are presented for illustrating its mechanism and predictive performance: crude oil price forecasting problem and tourist arrival forecasting. Empirical results support the fact that there is no one-fits-all methodology that outperforms in all periods. Our combination algorithm picks a different subset in each step, so the combination structure is dynamically redefined. Although some methodologies perform poorly, and they are never selected for the subset (e.g., ARIMA, ETS), most other methodologies are interchangeably picked or discarded from the combination structure. •Best possible combinations of forecasters to have better predictive performance.•Sparse weighting algorithm to combine forecasts to reduce forecasting error.•Linear combination of forecaster vs average and median combining methods.•Dynamic ensemble algorithm to combine forecasting results from multiple methodologies.•Self-calibrating forecasting algorithm combining various models.
Bibliografie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:0950-7051
1872-7409
DOI:10.1016/j.knosys.2021.107990