Counterfactual Optimal Action Trees (COAT): Interpretable Prescriptive Policies from Observational Data
For businesses with complex constraints and limited experimental flexibility, COAT provides transparent, data-driven policies that improve revenue, as demonstrated in a real-world airline deployment.
COAT learns interpretable prescriptive policies from observational data, combining counterfactual estimation with mixed-integer optimization. In a 17-week airline field pilot, it increased upsell revenue per booking by 6.9%, with projected $50-$150 million annual revenue gain.
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.