# Temporal Fusion Transformer for Multi-Horizon Probabilistic Forecasting of Weekly Retail Sales

arXiv: https://arxiv.org/abs/2511.00552 · HTML: https://mlsanity.com/paper/2511.00552/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 15 references that are in the map.
- First posted on arXiv 1 Nov 2025.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting](https://mlsanity.com/paper/2106.13008/) (2021)
- [FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting](https://mlsanity.com/paper/2201.12740/) (2022)
- [Temporal Fusion Transformers for Interpretable Multi-horizon Time Series Forecasting](https://mlsanity.com/paper/1912.09363/) (2019)
- [From Known to Unknown: Knowledge-guided Transformer for Time-Series Sales Forecasting in Alibaba](https://mlsanity.com/paper/2109.08381/) (2021)
- [Approaching sales forecasting using recurrent neural networks and transformers](https://mlsanity.com/paper/2204.07786/) (2022)
- [Probabilistic forecasting of heterogeneous consumer transaction-sales time series](https://mlsanity.com/paper/1808.04698/) (2018)

## Built on by (most cited first, 1 of 1)

- [CEDAR: Controlled and Event-Driven Demand Forecasting via Residual Decomposition](https://mlsanity.com/paper/2608.25871/) (2026)

## Abstract (arXiv)

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 R2 of 0.9875. Across a 5-fold chronological cross-validation, the averages are RMSE = 64.6k USD and R2 = 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.