用Transformer预测每周零售销售，精度高且可解释。
Temporal Fusion Transformer for Multi-Horizon Probabilistic Forecasting of Weekly Retail Sales
- 融合静态门店信息与动态外部变量，用TFT建模时间依赖
- 5周前瞻预测误差均值64.6千美元，决定系数达0.9844
- 结果可解释，适合库存管理和节假日促销优化
精准的多时域零售预测对库存和促销至关重要。本文基于2010--2012年沃尔玛45家门店的周销售数据，提出一种新型时序融合变压器（Temporal Fusion Transformer, TFT）模型，融合静态门店标识与随时间变化的外部信号（节假日、消费者价格指数、燃油价格、气温）。该模型通过分位数损失生成1--5周前瞻的概率性预测，获得校准的90%预测区间，并借助变量选择网络、静态特征增强与时间注意力机制实现可解释性。在固定2012年验证集上，TFT每店周均方根误差（RMSE）为57.9千美元，决定系数（R²）达0.9875；在5折时间交叉验证中，平均RMSE为64.6千美元，R²为0.9844，优于XGB、CNN、LSTM及CNN-LSTM基线模型。结果表明其在库存规划与节日期间优化中具有实际应用价值，同时保持模型透明性。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。