AI 中文总结
本研究针对多序列WaveNet销售预测模型，添加反事实可解释性层，通过删除/插入协议评估归因可信度，发现归因反映模型真实行为，同时明确其信息性的异质性与局限性。
AI 中文摘要
用于销售预测的深度模型（如WaveNet风格的膨胀卷积网络）精度高但可解释性差：当单个模型对多个序列中的某一个进行销售预测时，无法解释预测的原因。我们在基于完整的Corporacion Favorita杂货数据集（1688天内的174685个序列）训练的多序列WaveNet预测器上，添加了一个事后的、与架构无关的反事实可解释性层。该方法将每个预测分解为恰好总和等于预测值的贡献，避免了我们在加性SHAP风格归因中观察到的分配偏差。我们采用删除/插入协议评估可信度，发现两项测试均存在统计显著效应（删除差距为0.22，p<0.001；插入差距为0.27，p<0.01；在5个背景采样种子上具有鲁棒性），证明归因反映了模型的真实行为而非看似合理的偏差。随后我们如实描述了归因的信息性范围：不同序列对促销信号的依赖存在异质性（中位数比率约为1.0，约20%的序列表现出强效应），模型捕捉到了每周销售周期的形态（星期几的相关系数r=0.78），但系统性低估了其幅度。我们的贡献并非提升精度，而是提供了一个具有严格可信度评估并如实说明其局限性的可解释性层。
英文摘要
Deep models for sales forecasting, such as WaveNet-style dilated convolutional networks, are accurate but opaque: when a single model predicts sales for one of many series, it offers no account of why. We add a post-hoc, architecture-agnostic counterfactual interpretability layer to a multi-series WaveNet forecaster trained on the full Corporacion Favorita grocery dataset (174,685 series over 1,688 days). The method decomposes each forecast into contributions that sum exactly to the predicted value, avoiding the allocation artifacts we observed with additive SHAP-style attribution. We evaluate faithfulness with a deletion/insertion protocol and find a statistically significant effect on both tests (deletion gap 0.22, p<0.001; insertion gap 0.27, p<0.01; robust across five background-sampling seeds), establishing that the attributions reflect genuine model behavior rather than plausible-looking artifacts. We then characterize, honestly, where attribution is and is not informative: reliance on the promotion signal is heterogeneous across series (median ratio approximately 1.0, with roughly 20% of series showing a strong effect), and the model captures the shape of the weekly sales cycle (day-of-week r=0.78) while systematically under-predicting its amplitude. Our contribution is not improved accuracy but an interpretability layer with a rigorous faithfulness evaluation and a candid account of its limits.
CommentsCode: https://github.com/kesjien/wavexplain
