Exploring the sources of uncertainty: why does bagging for time series forecasting work?

DOI10.1016/j.ejor.2018.01.045zbMath1403.62169OpenAlexW2787031726MaRDI QIDQ1754348

Rob Hyndman, Fotios Petropoulos, Christoph Bergmeir

Publication date: 30 May 2018

Published in: European Journal of Operational Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.ejor.2018.01.045

zbMATH Keywords

aggregationuncertaintyforecastingbootstrappingmodel combination

Mathematics Subject Classification ID

Time series, auto-correlation, regression, etc. in statistics (GARCH) (62M10) Economic time series analysis (91B84)

Related Items

Model selection in reconciling hierarchical time series ⋮ Generalizing the Theta method for automatic forecasting ⋮ SETAR-Tree: a novel and accurate tree algorithm for global time series forecasting ⋮ Unnamed Item ⋮ Structural combination of seasonal exponential smoothing forecasts applied to load forecasting ⋮ Understanding forecast reconciliation ⋮ Multi-objective algorithm for the design of prediction intervals for wind power forecasting model ⋮ Frequency-based ensemble forecasting model for time series forecasting

Uses Software

• R
• forecast
• Forecast
• ElemStatLearn
• GitHub
• Boot.EXPOS

Cites Work

• Unnamed Item
• Unnamed Item
• Bagging predictors
• Sieve bootstrap for time series
• Forecasting for big data: does suboptimality matter?
• Outpatient appointment systems in healthcare: a review of optimization studies
• A retail store SKU promotions optimization model for category multi-period profit maximization
• Strategic facility location, capacity acquisition, and technology choice decisions under demand uncertainty: robust vs. non-robust optimization approaches
• The jackknife and the bootstrap for general stationary observations
• `Horses for courses' in demand forecasting
• Banded and tapered estimates for autocovariance matrices and the linear process bootstrap