Publication
INFORMS 2021
Talk

Ticket Pricing via Prescriptive Model Distillation

View publication

Abstract

Powerful blackbox machine learning models often lead to complex policies which are difficult to verify and manage. Biggs et. al 2021 proposed a decision tree approach to extract revenue-maximizing pricing policies which are also interpretable by separating the counterfactual estimation and policy learning steps. We implement this method on premium ticket pricing with a large international airline. Backtest results show that this method is capable of achieving significant improvement over the current pricing with just a few rules and it is being currently integrated into the analytics pipeline for a live pilot.

Date

Publication

INFORMS 2021

Authors

Share