Hotel Intelligence: Maximizing Revenue with Nonlinear Dynamic Pricing and Predictive Demand Analysis

  • Filipe Dwan Pereira CESAR Innovation Center / UFRR
  • George Zambonin CESAR Innovation Center / UFRR
  • Francisco Bráulio Oliveira CESAR Innovation Center
  • Christiano Penna CESAR Innovation Center
  • Gabriel Vasconcelos CESAR Innovation Center
  • Gabriel Barbosa CESAR Innovation Center
  • João Paulo Freitas CESAR Innovation Center
  • Pedro Dreyer CESAR Innovation Center
  • Ricardo Fernandes CESAR Innovation Center
  • Rafael Ferreira Mello CESAR Innovation Center / UFRR

Resumo


Dynamic pricing is fundamental for revenue maximization in the hotel industry, particularly given demand volatility. Machine Learning (ML) models offer a promising avenue for learning optimal pricing policies without necessitating direct market experimentation. However, evaluating the effectiveness of these models presents challenges, especially due to the scarcity of robust theoretical benchmarks. This study introduces a mathematical simulator employing constrained nonlinear programming to identify optimal daily rates across various pricing scenarios. The simulator is designed to serve as a reference for assessing the performance of ML-based pricing strategies. Simulations conducted demonstrate the model’s stability and its applicability for generating benchmark solutions in diverse operational contexts.
Publicado
29/09/2025
Como Citar

Selecione um Formato
PEREIRA, Filipe Dwan et al. Hotel Intelligence: Maximizing Revenue with Nonlinear Dynamic Pricing and Predictive Demand Analysis. In: BRAZILIAN CONFERENCE ON INTELLIGENT SYSTEMS (BRACIS), 35. , 2025, Fortaleza/CE. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2025 . p. 18-33. ISSN 2643-6264.