Home > Research > Publications & Outputs > A New Taxonomy for Vector Exponential Smoothing...

Links

Text available via DOI:

View graph of relations

A New Taxonomy for Vector Exponential Smoothing and Its Application to Seasonal Time Series

Research output: Contribution to Journal/MagazineJournal articlepeer-review

E-pub ahead of print

Standard

A New Taxonomy for Vector Exponential Smoothing and Its Application to Seasonal Time Series. / Svetunkov, Ivan; Chen, Huijing; Boylan, John E.

In: European Journal of Operational Research, 04.05.2022.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

APA

Vancouver

Author

Bibtex

@article{c5bdf0ae58c6416a8923391a6fe592df,
title = "A New Taxonomy for Vector Exponential Smoothing and Its Application to Seasonal Time Series",
abstract = "In short-term demand forecasting, it is often difficult to estimate seasonality accurately, owing to short data histories. However, companies usually have multiple products with similar seasonal demand patterns. A possible solution in this case is to use the components of several time series from a homogeneous family, thus estimating seasonal coefficients based on cross-sectional information. Motivated by this practical problem, we propose a new taxonomy of Parameters, Initial States and Components (PIC), which exploits homogeneous features of time series. We then apply this framework to vector exponential smoothing. We develop a model selection mechanism based on information criteria to select the appropriate PIC restrictions. We then conduct a simulation experiment and empirical analysis on retail data in order to assess the performance of point forecasts and prediction intervals of the models within this framework.",
keywords = "Forecasting, Multivariate statistics, Seasonal data, Vector exponential smoothing, Retailing",
author = "Ivan Svetunkov and Huijing Chen and Boylan, {John E.}",
year = "2022",
month = may,
day = "4",
doi = "10.1016/j.ejor.2022.04.040",
language = "English",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "Elsevier Science B.V.",

}

RIS

TY - JOUR

T1 - A New Taxonomy for Vector Exponential Smoothing and Its Application to Seasonal Time Series

AU - Svetunkov, Ivan

AU - Chen, Huijing

AU - Boylan, John E.

PY - 2022/5/4

Y1 - 2022/5/4

N2 - In short-term demand forecasting, it is often difficult to estimate seasonality accurately, owing to short data histories. However, companies usually have multiple products with similar seasonal demand patterns. A possible solution in this case is to use the components of several time series from a homogeneous family, thus estimating seasonal coefficients based on cross-sectional information. Motivated by this practical problem, we propose a new taxonomy of Parameters, Initial States and Components (PIC), which exploits homogeneous features of time series. We then apply this framework to vector exponential smoothing. We develop a model selection mechanism based on information criteria to select the appropriate PIC restrictions. We then conduct a simulation experiment and empirical analysis on retail data in order to assess the performance of point forecasts and prediction intervals of the models within this framework.

AB - In short-term demand forecasting, it is often difficult to estimate seasonality accurately, owing to short data histories. However, companies usually have multiple products with similar seasonal demand patterns. A possible solution in this case is to use the components of several time series from a homogeneous family, thus estimating seasonal coefficients based on cross-sectional information. Motivated by this practical problem, we propose a new taxonomy of Parameters, Initial States and Components (PIC), which exploits homogeneous features of time series. We then apply this framework to vector exponential smoothing. We develop a model selection mechanism based on information criteria to select the appropriate PIC restrictions. We then conduct a simulation experiment and empirical analysis on retail data in order to assess the performance of point forecasts and prediction intervals of the models within this framework.

KW - Forecasting

KW - Multivariate statistics

KW - Seasonal data

KW - Vector exponential smoothing

KW - Retailing

U2 - 10.1016/j.ejor.2022.04.040

DO - 10.1016/j.ejor.2022.04.040

M3 - Journal article

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

ER -