Optimization with constraint learning for pricing services under competition

Abstract

Revenue Management (RM) optimizes pricing and capacity allocation under demand uncertainty. We propose a data-driven RM framework that integrates neural networks or gradient boosting tree models with constraint learning to support joint pricing and capacity decisions. The approach adapts to arbitrary demand patterns learned directly from data, without requiring a predefined demand model, and captures competitive interactions between railway undertakings using only observable information. The methodology is illustrated through a case study of the Madrid-Barcelona high-speed rail corridor.

Code

The code for the experiments presented in this talk is available at GitHub under the Apache License 2.0. Please refer to the repository for instructions on how to reproduce the results and access the datasets used in the experiments. Note that the repository contains the current research implementation and the code is still under development, so it may change substantially before publication.