machine learning

Counterfactual Optimal Action Trees (COAT): Interpretable Prescriptive Policies from Observational Data

arXiv:2607.14318

summary

The paper presents COAT, a method that builds interpretable decision trees for prescribing actions by combining counterfactual outcome estimates with mixed‑integer optimization, and demonstrates its revenue impact in an airline pricing pilot.

Abstract

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.

Topics & keywords

#causal inference#prescriptive analytics#decision trees#mixed-integer optimization#airline revenue managementcounterfactual outcome estimationcolumn generationmixed-integer programmingobservational dataprescriptive policy
Counterfactual Optimal Action Trees (COAT): Interpretable Prescriptive Policies from Observational Data · wovepaper