1127. Learning-based pricing policies for substitutable itineraries
Invited abstract in session MA-29: Machine learning in pricing and revenue management, stream Pricing and Revenue Management Innovations.
Monday, 8:30-10:00Room: Maurice Keyworth 1.04
Authors (first author is the speaker)
| 1. | Yue Su
|
| Informatique, Université de Lille | |
| 2. | Antoine Désir
|
| ISEAD Business School | |
| 3. | Axel Parmentier
|
| CERMICS, Ecole des Ponts ParisTech |
Abstract
In airline revenue management, dynamic pricing for substitutable itineraries presents significant challenges due to the stochastic nature of customer choices. The dynamic pricing problem can be conceptualized as a Markov Decision Process with the objective of maximizing the total expected revenue over a finite selling horizon. However, the complexity of this model, characterized by its multi-dimensional state and action spaces, makes it computationally prohibitive to solve exactly, even for small-to-medium-sized instances. As a result, classic methods such as dynamic programming (DP) prove inefficient in addressing the dynamic pricing problem for larger instances. In this work, we introduce learning-based policies tailored to the dynamic pricing problem of substitute itineraries. We proposed two different machine learning (ML) pipelines to encode pricing policy and designed tailored training processes for each of them. Compared to existing methods, our approach has two advantages:(1) Benchmarking the proposed policies against the optimal pricing policy, we show that learning-based policies seem to be a good approximation for the optimal policy,(2) Our learning-based policies can lead to huge speed-up in solving large-scale instances (with up to million-magnitude state space) by moving all CPU time offline.
Keywords
- Revenue Management and Pricing
- Airline Applications
- Machine Learning
Status: accepted
Back to the list of papers