提升的广义正态分布：将机器学习与运营知识相结合
Boosted generalized normal distributions: Integrating machine learning with operations knowledge
AI总结：
本文提出提升的广义正态分布（$b$GND），用梯度提升灵活估计GND参数，并在急诊数据上证明其分布预测优于分布无关ML基准，且能提升患者满意度并降低死亡率。
摘要：
机器学习（ML）技术在运营场景中的应用常常面临两个挑战：其一，ML方法大多只提供点预测，而许多运营问题需要分布信息；其二，这些方法通常没有纳入运营文献中大量的知识体系，尤其是那些刻画特定分布的理论与实证发现。我们提出一种新颖且严谨的方法——提升的广义正态分布（$b$GND），以应对这些挑战。广义正态分布（GND）涵盖了运营中常见的一大类参数分布，而$b$GND利用基于树学习器的梯度提升方法，将GND的参数灵活地估计为协变量的函数。我们建立了$b$GND的统计一致性，从而将这一关键性质扩展到ML文献中研究的、此前缺乏此类保证的特殊情形。利用美国一个大型学术急诊科的数据，我们表明，通过借鉴医疗运营文献中的发现，患者等待时间和服务时间的分布预测可以得到有意义的改进。具体而言，与用于预测等待时间和服务时间的分布无关ML基准相比，$b$GND的表现分别提升了6%和9%。进一步分析表明，这些改进转化为患者满意度提高9%，以及心肌梗死患者死亡率降低4%。我们的工作强调了将机器学习与运营知识相结合以增强分布预测的重要性。
英文摘要：
Applications of machine learning (ML) techniques to operational settings often face two challenges: i) ML methods mostly provide point predictions whereas many operational problems require distributional information; and ii) They typically do not incorporate the extensive body of knowledge in the operations literature, particularly the theoretical and empirical findings that characterize specific distributions. We introduce a novel and rigorous methodology, the Boosted Generalized Normal Distribution ($b$GND), to address these challenges. The Generalized Normal Distribution (GND) encompasses a wide range of parametric distributions commonly encountered in operations, and $b$GND leverages gradient boosting with tree learners to flexibly estimate the parameters of the GND as functions of covariates. We establish $b$GND's statistical consistency, thereby extending this key property to special cases studied in the ML literature that lacked such guarantees. Using data from a large academic emergency department in the United States, we show that the distributional forecasting of patient wait and service times can be meaningfully improved by leveraging findings from the healthcare operations literature. Specifically, $b$GND performs 6% and 9% better than the distribution-agnostic ML benchmark used to forecast wait and service times respectively. Further analysis suggests that these improvements translate into a 9% increase in patient satisfaction and a 4% reduction in mortality for myocardial infarction patients. Our work underscores the importance of integrating ML with operations knowledge to enhance distributional forecasts.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
