Transformer-Based Models for Probabilistic Time Series Forecasting with Explanatory Variables
Accurate demand forecasting is essential for retail operations as it directly impacts supply chain efficiency, inventory management, and financial performance. However, forecasting retail time series presents significant challenges due to their irregular patterns, hierarchical structures, and strong...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-02-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/13/5/814 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850228178607407104 |
|---|---|
| author | Ricardo Caetano José Manuel Oliveira Patrícia Ramos |
| author_facet | Ricardo Caetano José Manuel Oliveira Patrícia Ramos |
| author_sort | Ricardo Caetano |
| collection | DOAJ |
| description | Accurate demand forecasting is essential for retail operations as it directly impacts supply chain efficiency, inventory management, and financial performance. However, forecasting retail time series presents significant challenges due to their irregular patterns, hierarchical structures, and strong dependence on external factors such as promotions, pricing strategies, and socio-economic conditions. This study evaluates the effectiveness of Transformer-based architectures, specifically Vanilla Transformer, Informer, Autoformer, ETSformer, NSTransformer, and Reformer, for probabilistic time series forecasting in retail. A key focus is the integration of explanatory variables, such as calendar-related indicators, selling prices, and socio-economic factors, which play a crucial role in capturing demand fluctuations. This study assesses how incorporating these variables enhances forecast accuracy, addressing a research gap in the comprehensive evaluation of explanatory variables within multiple Transformer-based models. Empirical results, based on the M5 dataset, show that incorporating explanatory variables generally improves forecasting performance. Models leveraging these variables achieve up to 12.4% reduction in Normalized Root Mean Squared Error (NRMSE) and 2.9% improvement in Mean Absolute Scaled Error (MASE) compared to models that rely solely on past sales. Furthermore, probabilistic forecasting enhances decision making by quantifying uncertainty, providing more reliable demand predictions for risk management. These findings underscore the effectiveness of Transformer-based models in retail forecasting and emphasize the importance of integrating domain-specific explanatory variables to achieve more accurate, context-aware predictions in dynamic retail environments. |
| format | Article |
| id | doaj-art-dba9e479a6844cd8a573fe94c5417711 |
| institution | OA Journals |
| issn | 2227-7390 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj-art-dba9e479a6844cd8a573fe94c54177112025-08-20T02:04:36ZengMDPI AGMathematics2227-73902025-02-0113581410.3390/math13050814Transformer-Based Models for Probabilistic Time Series Forecasting with Explanatory VariablesRicardo Caetano0José Manuel Oliveira1Patrícia Ramos2ISCAP, Polytechnic of Porto, Rua Jaime Lopes Amorim s/n, 4465-004 São Mamede de Infesta, PortugalInstitute for Systems and Computer Engineering, Technology and Science, Campus da FEUP, Rua Dr. Roberto Frias, 4200-465 Porto, PortugalInstitute for Systems and Computer Engineering, Technology and Science, Campus da FEUP, Rua Dr. Roberto Frias, 4200-465 Porto, PortugalAccurate demand forecasting is essential for retail operations as it directly impacts supply chain efficiency, inventory management, and financial performance. However, forecasting retail time series presents significant challenges due to their irregular patterns, hierarchical structures, and strong dependence on external factors such as promotions, pricing strategies, and socio-economic conditions. This study evaluates the effectiveness of Transformer-based architectures, specifically Vanilla Transformer, Informer, Autoformer, ETSformer, NSTransformer, and Reformer, for probabilistic time series forecasting in retail. A key focus is the integration of explanatory variables, such as calendar-related indicators, selling prices, and socio-economic factors, which play a crucial role in capturing demand fluctuations. This study assesses how incorporating these variables enhances forecast accuracy, addressing a research gap in the comprehensive evaluation of explanatory variables within multiple Transformer-based models. Empirical results, based on the M5 dataset, show that incorporating explanatory variables generally improves forecasting performance. Models leveraging these variables achieve up to 12.4% reduction in Normalized Root Mean Squared Error (NRMSE) and 2.9% improvement in Mean Absolute Scaled Error (MASE) compared to models that rely solely on past sales. Furthermore, probabilistic forecasting enhances decision making by quantifying uncertainty, providing more reliable demand predictions for risk management. These findings underscore the effectiveness of Transformer-based models in retail forecasting and emphasize the importance of integrating domain-specific explanatory variables to achieve more accurate, context-aware predictions in dynamic retail environments.https://www.mdpi.com/2227-7390/13/5/814transformerstime seriesprobabilistic forecastingretailcovariatesdeep learning |
| spellingShingle | Ricardo Caetano José Manuel Oliveira Patrícia Ramos Transformer-Based Models for Probabilistic Time Series Forecasting with Explanatory Variables Mathematics transformers time series probabilistic forecasting retail covariates deep learning |
| title | Transformer-Based Models for Probabilistic Time Series Forecasting with Explanatory Variables |
| title_full | Transformer-Based Models for Probabilistic Time Series Forecasting with Explanatory Variables |
| title_fullStr | Transformer-Based Models for Probabilistic Time Series Forecasting with Explanatory Variables |
| title_full_unstemmed | Transformer-Based Models for Probabilistic Time Series Forecasting with Explanatory Variables |
| title_short | Transformer-Based Models for Probabilistic Time Series Forecasting with Explanatory Variables |
| title_sort | transformer based models for probabilistic time series forecasting with explanatory variables |
| topic | transformers time series probabilistic forecasting retail covariates deep learning |
| url | https://www.mdpi.com/2227-7390/13/5/814 |
| work_keys_str_mv | AT ricardocaetano transformerbasedmodelsforprobabilistictimeseriesforecastingwithexplanatoryvariables AT josemanueloliveira transformerbasedmodelsforprobabilistictimeseriesforecastingwithexplanatoryvariables AT patriciaramos transformerbasedmodelsforprobabilistictimeseriesforecastingwithexplanatoryvariables |