用可解释的决策树优化机票附加销售，提升收入6.9%。
Counterfactual Optimal Action Trees (COAT): Interpretable Prescriptive Policies from Observational Data
- 基于反事实预测与优化算法，生成符合业务规则的可解释决策
- 17周试点中每单增收6.9%，年增收益预估5000万至1.5亿美元
- 适合需要透明、合规且可落地的智能决策场景
我们提出COAT（反事实最优行动树）框架，从观测数据中学习可解释的处方型策略。COAT将反事实结果估计与大规模混合整数优化结合，采用列生成法，在业务和监管约束下将因果预测转化为可行且透明的决策。我们在航空公司附加产品定价场景中应用该方法，该场景具有复杂商业规则且实验灵活性有限。在一家全球主要航空公司为期17周的实地试点中，COAT使每单预订的加价收入提升了6.9%，航空公司预计在符合条件的国内市场每年可新增5000万至1.5亿美元的高端座位收入。试点成功推动了全面推广，并支持了组织内更广泛的AI驱动决策计划。
原文摘要 · Abstract (English)
We introduce COAT (Counterfactual Optimal Action Tree), a framework for learning interpretable prescriptive policies from observational data. COAT combines counterfactual outcome estimation with large-scale mixed-integer optimization, using column generation to translate causal predictions into feasible, transparent decisions under business and regulatory constraints. We apply COAT to airline ancillary pricing, a setting characterized by complex business rules and limited experimental flexibility. In a 17-week field pilot with a major global airline, COAT increased upsell revenue per booking by 6.9%, with the airline projecting \$50-\$150 million in incremental annual premium seat revenue across eligible domestic markets. The success of the pilot led to scaled adoption and informed broader AI-driven decision initiatives within the organization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。