Market-Based and Policy-Based Conditional Demand Forecaster for Airline Revenue Management

The price transparency brought by the proliferation of online travel agencies and the loosening of fare class restrictions increases the importance of competitive pricing in the practice of airline revenue management. In this dissertation, we propose a novel forecasting framework, market-based and policy-based conditional demand forecaster (MPCF) to provide airline revenue management systems (RMSs) with dynamically adjusted sell-up probabilities and fare class demand forecasts based on estimated total market demand (market-based) and predicted fare class availabilities of competitors (policy-based) for a future flight departure. In the MPCF framework, an airline estimates the total market demand for travel on a future departure day and predicts its competing airline’s future fare class availabilities. The estimation of the total market demand allows the forecasting airline to anticipate additional demand when it offers lower fare quotes than its competitors and vice versa; the prediction of a competitor’s policy enables the revision of expected passenger sell-up probabilities to higher fares, conditioned on competitive influences and assumed passenger choice behaviors. In simulation tests, we assumed a Bertrand-Edgeworth passenger choice model, corresponding to a fully undifferentiated fare environment. With an assumption of perfect knowledge of total market demand that has already arrived for a future departure date, MPCF gains 12.69% in revenue compared with the existing Q-forecasting in an isolated market. Without that perfect knowledge, which requires estimation of total market demand, MPCF still gained 6.23% of revenue. MPCF leads to higher revenue gains on departures with demand levels that are different from the mean historical demand, demonstrating its benefits in providing dynamic sell-up and forecast guidance according to the predicted policies of competitors. The simulation results confirm the benefits of constructing demand forecasts on predicted market demand and competitors’ policies.

Name thesis:degree_name

Doctoral

Department dc:contributor.department

Massachusetts Institute of Technology. Department of Aeronautics and Astronautics

Grantor dc:publisher

Massachusetts Institute of Technology

Year dc:date.issued

2023

Author dc:creator

• Lu, Yuxuan

Advisor dc:contributor.advisor

• Belobaba, Peter P.

Statement dc:rights

• In Copyright - Educational Use Permitted
• Copyright retained by author(s)

Licence dc:rights.uri

• https://rightsstatements.org/page/InC-EDU/1.0/

Handle dc:identifier.uri

https://hdl.handle.net/1721.1/157811

OAI identifier oai:identifier

oai:dspace.mit.edu:1721.1/157811