An Agent for Optimizing Airline Ticket Purchasing

Buying airline tickets is an ubiquitous task in which it is difficult for humans to minimize cost due to insufficient information. Even with historical data available for inspection (a recent addition to some travel reservation websites), it is difficult to assess how purchase timing translates into changes in expected cost. To address this problem, we introduce an agent which is able to optimize purchase timing on behalf of customers. We provide results that demonstrate the method can perform much closer to the optimal purchase policy than existing decision theoretic approaches for this domain.

Authors

• William Groves
• Maria Gini

Keywords

• airline ticket prices
• feature selection
• PLS regression