[论文解读] Hierarchical Industrial Demand Forecasting with Temporal and Uncertainty Explanations

Harshavardhan Kamarthi, Shangqing Xu+5 more|arXiv (Cornell University)|Mar 6, 2026

Forecasting Techniques and Applications被引用 0

一句话总结

论文提出 HiereInterpret，一种可推广的方法，通过（1）子树近似以遵循层次结构，以及（2）基于分位数的确定性替代用于概率输出，对合成数据和真实工业数据进行评估，显著提升可解释性。

ABSTRACT

Hierarchical time-series forecasting is essential for demand prediction across various industries. While machine learning models have obtained significant accuracy and scalability on such forecasting tasks, the interpretability of their predictions, informed by application, is still largely unexplored. To bridge this gap, we introduce a novel interpretability method for large hierarchical probabilistic time-series forecasting, adapting generic interpretability techniques while addressing challenges associated with hierarchical structures and uncertainty. Our approach offers valuable interpretative insights in response to real-world industrial supply chain scenarios, including 1) the significance of various time-series within the hierarchy and external variables at specific time points, 2) the impact of different variables on forecast uncertainty, and 3) explanations for forecast changes in response to modifications in the training dataset. To evaluate the explainability method, we generate semi-synthetic datasets based on real-world scenarios of explaining hierarchical demands for over ten thousand products at a large chemical company. The experiments showed that our explainability method successfully explained state-of-the-art industrial forecasting methods with significantly higher explainability accuracy. Furthermore, we provide multiple real-world case studies that show the efficacy of our approach in identifying important patterns and explanations that help stakeholders better understand the forecasts. Additionally, our method facilitates the identification of key drivers behind forecasted demand, enabling more informed decision-making and strategic planning. Our approach helps build trust and confidence among users, ultimately leading to better adoption and utilization of hierarchical forecasting models in practice.

研究动机与目标

• 解决工业需求的大规模分层概率时间序列预测缺乏可解释性的问题。
• 开发一个通用的解释方法，尊重层次一致性与概率输出。
• 创建一个带有真实解释地面的半合成基准，并在真实世界的工业数据上验证。
• 展示解释如何揭示关键驱动因素、关键时间步和对数据变化的敏感性，以辅助决策制定。

提出的方法

• 提出子树近似，将跨层次的重要性分解为相邻层次的重要性，降低计算量并与层次一致性对齐。
• 通过输出分布的分位数引入一个概率预报的确定性替代，使现有方法实现事后可解释性。
• 通过生成具有已知真实解释的分层序列并将其嫁接到真实数据集上，建立合成基准以评估可解释性指标。
• 在确定性和概率设置下，使用重要性准确度分数（IAS）和外部变量检测准确度（EVDA）等指标评估解释。
• 提供基于Dow需求数据的真实世界案例研究，展示实际可解释性提升与利益相关者的实用性。

Figure 1: In real-world HTSF tasks, stakeholders and planners want to know: RQ1: which input variable(s) contribute most to the prediction; RQ2: which time steps of each variable contribute most to the prediction; RQ3: why prediction results change when input data changes.

实验结果

研究问题

• RQ1 RQ1: 在层次结构下，哪些变量对 HTSF 预测贡献最大？
• RQ2 RQ2: 输入历史中的哪些时间步对分层预测影响最大？
• RQ3 RQ3: 当输入数据被修改时，预测解释将如何变化？
• RQ4 RQ4: 如何使用确定性替代方法解释概率 HTSF 输出？
• RQ5 RQ5: 所 proposed 的解释方法是否可扩展到大型工业层次结构和真实数据集？

主要发现

• 子树近似在大层次结构中实现显著的可解释性提升，在确定性和概率设置下均有明显改进。
• 确定性分位数替代使得将标准解释方法应用于概率预测成为可能，得到一致的解释。
• 在合成基准中，子树近似使点预测解释（IAS）提高最多62.0%，概率解释（IAS）提高最多26.0%（平均）。
• 在真实世界的 Dow 数据及其他基准（M5、Tourism-L、Wiki）上，该方法在多种基线模型和 HTSF 模型上提升了可解释性指标。
• 案例研究表明该方法有助于识别关键驱动、模式及与利益相关者决策相关的不确定性变化。

Figure 2: Subtree approximation allows HiereInterpret to accurately capture importance scores of any time-series across the hierarchy