Forecast with forecasts: Diversity matters

@article{Kang2022ForecastWF,
  title={Forecast with forecasts: Diversity matters},
  author={Yanfei Kang and Wei Cao and Fotios Petropoulos and Feng Li},
  journal={Eur. J. Oper. Res.},
  year={2022},
  volume={301},
  pages={180-190}
}

Figures and Tables from this paper

Bayesian forecast combination using time-varying features
TLDR
A novel framework for density forecast combination by constructing time-varying weights based on time- varying features via Bayesian log predictive scores, in which the optimal forecast combination is determined by time series features from historical information.
Feature-based intermittent demand forecast combinations: bias, accuracy and inventory implications
Intermittent demand forecasting is a ubiquitous and challenging problem in opera-tions and supply chain management. There has been a growing focus on developing forecasting approaches for
Forecast combinations: an over 50-year review
Forecast combinations have flourished remarkably in the forecasting community and, in recent years, have become part of the mainstream of forecasting research and activities. Combining multiple
Improving forecasting by subsampling seasonal time series
TLDR
This work constructs multiple time series with different sub-seasons from the original time series, making it possible for the forecasting methods to capture diverse patterns and components of the data.
Sparse convex combinations of forecasting models by meta learning
Feature-based Bayesian forecasting model averaging
TLDR
This work proposes a novel framework for density forecast combination by constructing time-varying weights based on time series features, which is called Feature-based Bayesian Forecasting Model Averaging (FEBAMA), which has better interpretability compared to other black-box forecasting combination schemes.

References

SHOWING 1-10 OF 87 REFERENCES
Combining forecasts: A review and annotated bibliography
Combining forecasts: Performance and coherence
Combination forecasts of output growth in a seven-country data set
This paper uses forecast combination methods to forecast output growth in a seven-country quarterly economic data set covering 1959-1999, with up to 73 predictors per country. Although the forecasts
Principles of forecasting : a handbook for researchers and practitioners
TLDR
The author’s aim is to contribute to the public understanding of forecasting and its role in the private sector by promoting awareness of the importance of informed consent in the decision-making process.
Que ser\'a ser\'a? The uncertainty estimation of feature-based time series forecasts
TLDR
This paper proposes a general feature-based time series forecasting framework and introduces a threshold ratio for the selection of individual forecasting methods in this process, which outperforms all individual benchmark forecasting methods on M3 competition data with an improved computational efficiency.
GRATIS: GeneRAting TIme Series with diverse and controllable characteristics
TLDR
This work proposes GeneRAting TIme Series with diverse and controllable characteristics, named GRATIS, with the use of mixture autoregressive (MAR) models, and demonstrates the usefulness of the time series generation process through a time series forecasting application.
FFORMPP: Feature-based forecast model
  • 2021
Retail sales forecasting with meta-learning
...
1
2
3
4
5
...