Dynamic Pricing and Algorithm Design for Enhanced Ride-Sharing Services

The Gustave Eiffel University is a national multi-campus university. It was created on 1 January 2020 as a result of the merger of the University of Paris-Est Marne la Vallée, Ifsttar, and several schools and engineering schools: EIVP, ENSG, ESIEE, and Ecole d'architecture Paris Est. Gustave Eiffel University is Ranked 1st in Civil and Transportation engineering in France (ShanghaiRanking 2024) and has more than 2,500 agents and 17,000 students at nine sites in France. The university hosts a quarter of the national research and development on sustainable cities and is home to the largest transport research center in Europe.It is a university on a human scale, bringing together multi-disciplinary skills that enable it to conduct quality research for the benefit of society, to offer training courses adapted to the socio-economic world, and to support changes in society and public policies.

 The GRETTIA research lab is part of Université Gustave Eiffel and carries out its research activity in the field of land transport systems. It is interested in all aspects of road and guided transport modes, from systemic aspects, modeling and simulation to the dynamic aspects of vehicles, including management, diagnosis and maintenance. GRETTIA contributes to the development of transport network and system engineering, taking into consideration the issues of integration, intermodality, reliability and system analysis. Within this framework, the research unit conducts a transversal activity of development of models and generic tools based on the field of mathematical engineering, advanced computer science and mechanics; contributes to the modeling, design, management,evaluation and maintenance of intelligent transport and infrastructure operation systems; studies the conditions of functional and social acceptability of new transport services.

Efficient dynamic pricing and algorithm design in ride-sharing services are pivotal for optimizing service quality, profitability, and user satisfaction. Current methodologies often face challenges in balancing operational efficiency with fairness and market adaptability in dynamic urban environments. This internship focuses on developing an innovative algorithmic framework that integrates dynamic pricing strategies with real-time optimization to enhance ride-sharing services' operational performance.

Ride-sharing platforms must tackle the complexities of varying passenger demand, traffic conditions, and socio-economic preferences for pricing. Dynamic pricing and real-time optimization provide a means to improve resource allocation, boost user engagement, and increase overall system robustness. This internship will leverage advanced optimization algorithms, demand modeling, and simulation tools to address these challenges.

Objectives:

• Conduct a comprehensive literature review on dynamic pricing models and algorithms.
• Preprocess and analyze datasets related to ride-sharing services, including passenger demand, pricing elasticity, and traffic patterns.
• Develop a dynamic pricing algorithm considering travel distances, rider socio-economic profiles, and real-time traffic conditions.
• Integrate the pricing model with a novel ride-matching algorithm based on penalized optimization.
• Simulate and evaluate the proposed framework using real-world datasets to assess performance under various scenarios.
• Propose adaptive strategies for implementation in real-world dynamic ride-sharing systems.

References:

[1]. Alisoltani, Negin, Younes Delhoum, Mostafa Ameli, and Mahdi Zargayouna. "Enhancing Urban Mobility Through Peer-to-Peer Ride-Sharing: A System-Wide Impact Assessment." In Proceedings of the 2nd ACM SIGSPATIAL Workshop on Sustainable Urban Mobility, pp. 18-26. 2024.

[2] Alisoltani, Negin, Mahdi Zargayouna, and Mostafa Ameli. "Optimising ride-sharing efficiency: innovative shareability-focused pricing strategies." Transportmetrica B: Transport Dynamics 12, no. 1 (2024): 2417252.

Education: Master's level in one of the fields of applied mathematics, computer science, or transportation engineering.

Main skills: Proficiency in algorithm design, optimization methods, and data analysis. Knowledge of transportation systems and dynamic pricing concepts is a plus. Strong programming skills (Java, Python, or related languages). Excellent communication skills in English (reading and writing).

Know-how: Autonomy, problem-solving, teamwork, and a rigorous approach to experimental research.