Temporal Fusion Transformer for Multi-Horizon Probabilistic Forecasting of Weekly Retail Sales
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912683150802944 |
|---|---|
| author | Punati, Santhi Bharath Kanta, Sandeep Cheerala, Udaya Bhasker Lanjewar, Madhusudan G Damacharla, Praveen |
| author_facet | Punati, Santhi Bharath Kanta, Sandeep Cheerala, Udaya Bhasker Lanjewar, Madhusudan G Damacharla, Praveen |
| contents | Accurate multi-horizon retail forecasts are critical for inventory and promotions. We present a novel study of weekly Walmart sales (45 stores, 2010--2012) using a Temporal Fusion Transformer (TFT) that fuses static store identifiers with time-varying exogenous signals (holidays, CPI, fuel price, temperature). The pipeline produces 1--5-week-ahead probabilistic forecasts via Quantile Loss, yielding calibrated 90\% prediction intervals and interpretability through variable-selection networks, static enrichment, and temporal attention. On a fixed 2012 hold-out dataset, TFT achieves an RMSE of \$57.9k USD per store-week and an $R^2$ of 0.9875. Across a 5-fold chronological cross-validation, the averages are RMSE = \$64.6k USD and $R^2$ = 0.9844, outperforming the XGB, CNN, LSTM, and CNN-LSTM baseline models. These results demonstrate practical value for inventory planning and holiday-period optimization, while maintaining model transparency. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00552 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Temporal Fusion Transformer for Multi-Horizon Probabilistic Forecasting of Weekly Retail Sales Punati, Santhi Bharath Kanta, Sandeep Cheerala, Udaya Bhasker Lanjewar, Madhusudan G Damacharla, Praveen Machine Learning Artificial Intelligence General Economics Economics Accurate multi-horizon retail forecasts are critical for inventory and promotions. We present a novel study of weekly Walmart sales (45 stores, 2010--2012) using a Temporal Fusion Transformer (TFT) that fuses static store identifiers with time-varying exogenous signals (holidays, CPI, fuel price, temperature). The pipeline produces 1--5-week-ahead probabilistic forecasts via Quantile Loss, yielding calibrated 90\% prediction intervals and interpretability through variable-selection networks, static enrichment, and temporal attention. On a fixed 2012 hold-out dataset, TFT achieves an RMSE of \$57.9k USD per store-week and an $R^2$ of 0.9875. Across a 5-fold chronological cross-validation, the averages are RMSE = \$64.6k USD and $R^2$ = 0.9844, outperforming the XGB, CNN, LSTM, and CNN-LSTM baseline models. These results demonstrate practical value for inventory planning and holiday-period optimization, while maintaining model transparency. |
| title | Temporal Fusion Transformer for Multi-Horizon Probabilistic Forecasting of Weekly Retail Sales |
| topic | Machine Learning Artificial Intelligence General Economics Economics |
| url | https://arxiv.org/abs/2511.00552 |