4 Presentations

• 
  10:30 AM - 10:55 AM

  Optimizing Ticket Pricing with ExPretio's AI ​

  • Thibault Barbier, presenter, ExPretio
  • Adrien Dessinges, ExPretio

  ExPretio emerges from two decades of academic research in pricing and revenue optimization, integrating expertise from revenue management practitioners and operations research / data science specialists. Focused on helping rail passenger carriers better manager their capacity and pricing to maximize revenue, our challenge lay in understanding the intricate relationships between price, business rules, and passenger buying behaviors. Our AI-powered solution employs an interconnection of mathematical programming, machine learning, and simulation. Every day, we solve more than 125,000 mathematical programs, generating 60 million forecasts for over 20 global clients. This enables precise resource allocation, empowering rail companies to achieve revenue goals while considering broader business objectives. In our presentation, we will discuss our AI framework, the diverse challenges it addresses, and how we continue to collaborate with universities to improve our chain.

• 
  10:55 AM - 11:20 AM

  model-based quantification of the benefits and costs of developing a Canadian hydrogen network

  • Carlyle Deligny, presenter, Artelys

  In the context of the energy transition and the shift towards low-carbon systems, Artelys has conducted several studies in North America, leveraging its power system modeling tool Artelys Crystal Super Grid.
  This abstract introduces H2Clip, an ongoing research and development project focused on modeling the Canadian power system hydrogen potential. The primary objective of this endeavor is to project the evolution of the Canadian electrical system up to 2035 and assess the potential role of hydrogen within it. The presentation will delve into the development of a tool for conducting Hydrogen Infrastructure Cost-Benefit Analysis (CBA). This tool, designed to analyze various use cases, will serve as proof-of-concept for the development of hydrogen infrastructure. It will offer a diverse range of parameters and assets for investment consideration, enabling a detailed representation of specific projects.
  Through this abstract, we aim to showcase the innovative approach of H2Clip in exploring and modeling the integration of hydrogen within the Canadian power system and its potential implications for the energy landscape.

• 
  11:20 AM - 11:45 AM

  Créer des tournées postales opérationnelles à moindre coût avec GEOROUTE

  • Samuel Rosat, presenter, GIRO Inc.

  GIRO propose des logiciels qui optimisent la planification et la gestion des opérations des sociétés de transport public (bus et transport ferroviaire de passagers) et d’opérations postales dans plus de 25 pays à travers le monde. Nos algorithmes sont non seulement réputés pour leur puissance d’optimisation, mais aussi pour leur flexibilité permettant ainsi de s’adapter à la réalité spécifique de chaque client. Cette présentation se concentrera sur certains aspects spécifiques du domaine postal. En particulier, nous discuterons des enjeux liés aux algorithmes de création et d’ordonnancement de tournées de livraisons postales garantissant la stabilité des solutions d’un jour à l’autre alors que la charge de travail varie. Une trop grande instabilité génère une perte d’efficacité opérationnelle pouvant dépasser le gain théorique obtenu en optimisant selon des coûts basés sur le temps de travail et la distance parcourue. Notre cadre d’application requiert de trouver des solutions proches de l’optimalité dans des temps d’exécution de quelques dizaines de secondes tout en étant capable de prendre en compte les critères de stabilité. Nous présenterons certains cas concrets, détaillerons les approches de résolution ainsi que les critères de succès des projets développés en collaboration avec nos clients.

• 
  11:45 AM - 12:10 PM

  Leveraging Data-Driven Machine Learning for Strategic Network Planning Across Long and Intermediate Time Horizons in Aviation Industry

  • Zohreh Hajabedi, Olivier G Leblanc, presenter,
  • Marwen Naim,
  • Olivier G Leblanc,
  • Tianjiao Liu,
  • Zohreh Hajabedi, Air Canada
  • Charaf-Ed-Dine El Fattahi,
  • Ananya Sain Dhawan,
  • Tuan-Minh Vu,
  • Shenjun Lin,
  • Elisabeth Lamarche,

  In the aviation industry, data-driven decision support systems are instrumental for network planners to design intelligent networks and scope out new market opportunities, both of which ultimately lead to maximized profitability.
  The market size forecast that indicates the number of passengers willing to travel between a city pair, is a strong pilar for planning operations, pricing, and resource allocation. The more precise this forecast is, the more it contributes to making smart strategic decisions.
  The current market size forecasts used by most network planners are largely based on the expert intuition using general economic trends. We have leveraged the power of machine learning to develop demand forecasting models. The models consider the demand historical patterns, economics outlook - reflecting the purchasing power and behavior of consumers in origins and destinations - and capacity which reflects the market stability and competition landscape. Considering these indicators, models would be able to provide a comprehensive view of the market demand dynamics. Further, the system enables network planners to simulate what-if scenarios for capacity planning and based on the system predictions per scenario, they will observe the impact of capacity shock on the market behavior in the future.