标题： 用于周零售销售多时间步概率预测的时序融合变压器 显示英文标题

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

摘要： 准确的多时间范围零售预测对于库存和促销至关重要。我们提出了一项新的研究，使用时间融合变换器（TFT）对每周沃尔玛销售数据（45家门店，2010--2012年）进行分析，该模型融合了静态门店标识符与随时间变化的外部信号（节假日、CPI、燃油价格、温度）。该流程通过分位数损失生成1--5周 ahead 的概率预测，产生校准的90%预测区间，并通过变量选择网络、静态增强和时间注意力实现可解释性。在固定的2012年保留数据集上，TFT每店周的RMSE为57.9千美元，$R^2$为0.9875。在5折时间序列交叉验证中，平均值为RMSE = 64.6千美元和$R^2$= 0.9844，优于XGB、CNN、LSTM和CNN-LSTM基线模型。这些结果展示了在库存规划和节假日优化方面的实际价值，同时保持了模型的透明度。 显示英文摘要

摘要： 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.