Home > Research > Publications & Outputs > Retail sales forecasting with meta-learning

Electronic data

  • Retail sales forecasting with meta learning_0329

    Rights statement: This is the author’s version of a work that was accepted for publication in European Journal of Operational Research. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in European Journal of Operational Research, 288 (1), 2020 DOI: 10.1016/j.ejor.2020.05.038

    Accepted author manuscript, 1.29 MB, PDF document

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Links

Text available via DOI:

View graph of relations

Retail sales forecasting with meta-learning

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Published

Standard

Retail sales forecasting with meta-learning. / Ma, Shaohui; Fildes, Robert.

In: European Journal of Operational Research, Vol. 288, No. 1, 01.01.2021, p. 111-128.

Research output: Contribution to Journal/MagazineJournal articlepeer-review

Harvard

Ma, S & Fildes, R 2021, 'Retail sales forecasting with meta-learning', European Journal of Operational Research, vol. 288, no. 1, pp. 111-128. https://doi.org/10.1016/j.ejor.2020.05.038

APA

Ma, S., & Fildes, R. (2021). Retail sales forecasting with meta-learning. European Journal of Operational Research, 288(1), 111-128. https://doi.org/10.1016/j.ejor.2020.05.038

Vancouver

Ma S, Fildes R. Retail sales forecasting with meta-learning. European Journal of Operational Research. 2021 Jan 1;288(1):111-128. Epub 2020 May 28. doi: 10.1016/j.ejor.2020.05.038

Author

Ma, Shaohui ; Fildes, Robert. / Retail sales forecasting with meta-learning. In: European Journal of Operational Research. 2021 ; Vol. 288, No. 1. pp. 111-128.

Bibtex

@article{05aa965bdb17419998f4a8e1191035e1,
title = "Retail sales forecasting with meta-learning",
abstract = "Retail sales forecasting often requires forecasts for thousands of products for many stores. We present a meta-learning framework based on newly developed deep convolutional neural networks, which can first learn a feature representation from raw sales time series data automatically, and then link the learnt features with a set of weights which are used to combine a pool of base-forecasting methods. The experiments which are based on IRI weekly data show that the proposed meta-learner provides superior forecasting performance compared with a number of state-of-art benchmarks, though the accuracy gains over some more sophisticated meta ensemble benchmarks are modest and the learnt features lack interpretability. When designing a meta-learner in forecasting retail sales, we recommend building a pool of base-forecasters including both individual and pooled forecasting methods, and target finding the best combination forecasts instead of the best individual method.",
keywords = "Forecasting, Big data, Retail sales forecasting, Machine learning, Forecasting many time series, Deep learning, Meta-learning",
author = "Shaohui Ma and Robert Fildes",
note = "This is the author{\textquoteright}s version of a work that was accepted for publication in European Journal of Operational Research. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in European Journal of Operational Research, 288 (1), 2020 DOI: 10.1016/j.ejor.2020.05.038",
year = "2021",
month = jan,
day = "1",
doi = "10.1016/j.ejor.2020.05.038",
language = "English",
volume = "288",
pages = "111--128",
journal = "European Journal of Operational Research",
issn = "0377-2217",
publisher = "Elsevier Science B.V.",
number = "1",

}

RIS

TY - JOUR

T1 - Retail sales forecasting with meta-learning

AU - Ma, Shaohui

AU - Fildes, Robert

N1 - This is the author’s version of a work that was accepted for publication in European Journal of Operational Research. Changes resulting from the publishing process, such as peer review, editing, corrections, structural formatting, and other quality control mechanisms may not be reflected in this document. Changes may have been made to this work since it was submitted for publication. A definitive version was subsequently published in European Journal of Operational Research, 288 (1), 2020 DOI: 10.1016/j.ejor.2020.05.038

PY - 2021/1/1

Y1 - 2021/1/1

N2 - Retail sales forecasting often requires forecasts for thousands of products for many stores. We present a meta-learning framework based on newly developed deep convolutional neural networks, which can first learn a feature representation from raw sales time series data automatically, and then link the learnt features with a set of weights which are used to combine a pool of base-forecasting methods. The experiments which are based on IRI weekly data show that the proposed meta-learner provides superior forecasting performance compared with a number of state-of-art benchmarks, though the accuracy gains over some more sophisticated meta ensemble benchmarks are modest and the learnt features lack interpretability. When designing a meta-learner in forecasting retail sales, we recommend building a pool of base-forecasters including both individual and pooled forecasting methods, and target finding the best combination forecasts instead of the best individual method.

AB - Retail sales forecasting often requires forecasts for thousands of products for many stores. We present a meta-learning framework based on newly developed deep convolutional neural networks, which can first learn a feature representation from raw sales time series data automatically, and then link the learnt features with a set of weights which are used to combine a pool of base-forecasting methods. The experiments which are based on IRI weekly data show that the proposed meta-learner provides superior forecasting performance compared with a number of state-of-art benchmarks, though the accuracy gains over some more sophisticated meta ensemble benchmarks are modest and the learnt features lack interpretability. When designing a meta-learner in forecasting retail sales, we recommend building a pool of base-forecasters including both individual and pooled forecasting methods, and target finding the best combination forecasts instead of the best individual method.

KW - Forecasting

KW - Big data

KW - Retail sales forecasting

KW - Machine learning

KW - Forecasting many time series

KW - Deep learning

KW - Meta-learning

U2 - 10.1016/j.ejor.2020.05.038

DO - 10.1016/j.ejor.2020.05.038

M3 - Journal article

VL - 288

SP - 111

EP - 128

JO - European Journal of Operational Research

JF - European Journal of Operational Research

SN - 0377-2217

IS - 1

ER -