Smart Cards Enabled Agent-Based Models for Revenue Management in Public Transportation
Speakers
Abstract
|
Sustainable Revenue Management: A Smart Cards Enabled Agent-Based Modeling Approach Speaker: Milan Lovric |
| Public transportation operators (PTOs) function not only in an increasingly competitive environment, but also in a sensitive societal context that demands innovative approaches to revenue management. We propose a new, sustainable perspective on revenue management that considers individual customers' needs and environmental impacts in addition to PTO’s financial viability. We evaluated this perspective using an agent-based simulation approach and smart card transportation data. The results suggest that, by taking a customer-centric view, PTOs can better explore the space of feasible solutions to find more justifiable revenue management strategies that can lead to a sustainable situation. |
| An Agent-Based Simulation for Revenue Management in High-Speed Passenger Railways Speaker: Milan Lovric Authors: Milan Lovric, Yun Bao, Ting Li and Peter Vervest |
| In this paper we propose an agent-based simulation for revenue management in passenger-dedicated high-speed railway, with applications to Chinese and Dutch transportation systems. We developed our simulation models using capacity utilization data obtained from major transport operators. The results of this comparative study suggest that in both systems PTOs can influence railway passenger demand by using time-based pricing strategies, which has implications both on their financial performance and their customer satisfaction level. |
| Recognizing Demand Patterns from Smart Card Data for Agent-Based Microsimulation of Public Transport Speaker: Paul Bouman Authors: Paul Bouman, Milan Lovric, Ting Li, Evelien van der Hurk, Leo Kroon and Peter Vervest |
| In public transportation, finding a match between demand and capacity is essential for operators to provide high quality service with reasonable costs. Agent-based microsimulation is a promising method to address this problem, with recent applications to several large-scale scenarios. With the advent of smart card ticketing systems, new opportunities to generate an agent population have surfaced. In this study, we use a unique smart card dataset containing four months of individual mobility data in three modes of Dutch urban public transportation. We model the temporal flexibility of agents based on the patterns observed in check-in/check-out behavior of individual travelers. We then run simulations to study how agent populations react to a discounted tariff in the peak hours. Finally, we discuss opportunities for future research. |
| Contact information: |
| Dr. Wolf Ketter |
