This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Evaluating the Effectiveness of Time Series Transformers for Demand Forecasting in Retail
by
José Manuel Oliveira
José Manuel Oliveira 1,2,*,† and
Patrícia Ramos
Patrícia Ramos 2,3,†
1
Faculty of Economics, University of Porto, Rua Dr. Roberto Frias, 4200-464 Porto, Portugal
2
Institute for Systems and Computer Engineering, Technology and Science, Campus da FEUP, Rua Dr. Roberto Frias, 4200-465 Porto, Portugal
3
CEOS.PP, ISCAP, Polytechnic of Porto, Rua Jaime Lopes Amorim s/n, 4465-004 São Mamede de Infesta, Portugal
*
Author to whom correspondence should be addressed.
†
These authors contributed equally to this work.
Mathematics 2024, 12(17), 2728; https://doi.org/10.3390/math12172728 (registering DOI)
Submission received: 27 July 2024
/
Revised: 26 August 2024
/
Accepted: 29 August 2024
/
Published: 31 August 2024
Abstract
This study investigates the effectiveness of Transformer-based models for retail demand forecasting. We evaluated vanilla Transformer, Informer, Autoformer, PatchTST, and temporal fusion Transformer (TFT) against traditional baselines like AutoARIMA and AutoETS. Model performance was assessed using mean absolute scaled error (MASE) and weighted quantile loss (WQL). The M5 competition dataset, comprising 30,490 time series from 10 stores, served as the evaluation benchmark. The results demonstrate that Transformer-based models significantly outperform traditional baselines, with Transformer, Informer, and TFT leading the performance metrics. These models achieved MASE improvements of 26% to 29% and WQL reductions of up to 34% compared to the seasonal Naïve method, particularly excelling in short-term forecasts. While Autoformer and PatchTST also surpassed traditional methods, their performance was slightly lower, indicating the potential for further tuning. Additionally, this study highlights a trade-off between model complexity and computational efficiency, with Transformer models, though computationally intensive, offering superior forecasting accuracy compared to the significantly slower traditional models like AutoARIMA. These findings underscore the potential of Transformer-based approaches for enhancing retail demand forecasting, provided the computational demands are managed effectively.
Share and Cite
MDPI and ACS Style
Oliveira, J.M.; Ramos, P.
Evaluating the Effectiveness of Time Series Transformers for Demand Forecasting in Retail. Mathematics 2024, 12, 2728.
https://doi.org/10.3390/math12172728
AMA Style
Oliveira JM, Ramos P.
Evaluating the Effectiveness of Time Series Transformers for Demand Forecasting in Retail. Mathematics. 2024; 12(17):2728.
https://doi.org/10.3390/math12172728
Chicago/Turabian Style
Oliveira, José Manuel, and Patrícia Ramos.
2024. "Evaluating the Effectiveness of Time Series Transformers for Demand Forecasting in Retail" Mathematics 12, no. 17: 2728.
https://doi.org/10.3390/math12172728
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.