研究人员开发了一个新的框架，用于持续审计条件分位数预测器，这对于供应链管理等领域的顺序决策至关重要。该方法通过考虑数据漂移和模式变化，并认识到校准可能依赖于信息，从而解决了现有回测的局限性。该框架提供了特征感知的校准失误证据，实证测试显示 Chronos-2 预测模型在多个相关特征上表现出显著的校准失误。 AI
影响 这项研究为关键应用中 AI 预测模型的评估和可靠性保证提供了改进的方法。
排序理由 该集群包含一篇关于预测模型新审计框架的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2607.11653v1 Announce Type: cross Abstract: Black-box conditional quantile forecasts are widely used for sequential decisions under asymmetric costs, such as inventory planning in supply chain management. Once deployed, such forecasters must be monitored continuously as dat…
Black-box conditional quantile forecasts are widely used for sequential decisions under asymmetric costs, such as inventory planning in supply chain management. Once deployed, such forecasters must be monitored continuously as data streams drift and regimes change; this invalidat…