提出了一种名为决策-价值归因（DVA）的新框架，以更好地解释预测模型对运营决策的影响。与关注预测准确性的标准方法不同，DVA归因于整个预测-优化流程的价值。这种方法定义了合作博弈，其中参与者代表信息来源或优化参数，从而量化从特征、运营配置及其交互中获得的价值。案例研究表明，DVA可以比单独的预测解释提供更准确的运营价值见解，指导干预并确定预测信息在何时与决策最相关。 AI
影响 提供了一种更准确的方法来理解AI预测如何影响现实世界的运营决策，从而可能改进系统设计和干预策略。
排序理由 该集群包含一篇详细介绍新AI模型解释框架的研究论文。[lever_c_demoted from research: ic=1 ai=1.0]
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.29878v1 Announce Type: cross Abstract: Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce. This distinction is important in predict-th…
Predictive models are increasingly embedded in operational decision-making, yet standard explanation methods typically explain forecasts rather than the decisions those forecasts induce. This distinction is important in predict-then-optimize systems: large forecast changes may le…