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
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
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 -