Crowdshipping, a rapidly growing Last-Mile Delivery (LMD) model, leverages independent crowdworkers to fulfill delivery orders. Building a sustainable crowdshipper network is vital, with fair pay serving as a key driver of participation, especially for those who rely on these platforms as their primary source of income. Therefore, equitable workload allocation and compensation is ecpted to  benefit both platforms and workers. However, popular equity measures are often highly nonlinear, complicating the direct application of exact solution methods in the LMD context. To address this challenge, we explore a problem variant that adopts the Nash Social Welfare (NSW) equity measure, aiming to balance equity and efficiency while capping deviations from the least-cost solution. We model LMD with crowdshippers as a vehicle routing problem featuring a nonlinear NSW-inspired objective. A column generation method is developed, and computational experiments analyze how company costs, driver profits, and equity vary under different parameter settings. We then broaden the focus to address critical research questions in this domain: How should equity be measured? What are the costs associated with pursuing fairness? How can potential drawbacks be mitigated? Answering these questions requires a flexible tool capable of bi-objective optimization analysis. Due to the problem’s complexity, we develop a heuristic-based bi-objective optimization framework. This framework balances cost and equity, accommodates multiple equity measures, and approximates optimal trade-offs between fairness and efficiency. Our findings reveal that even minor sacrifices in cost efficiency can lead to up to 39% improvements in equity. We provide actionable recommendations, including guidance on selecting appropriate equity measures. Experiments further show that higher levels of equity are achieved when the crowdshipper pool remains small. We also quantify the performance loss among workers as the pool size grows, offering valuable insights for workforce planning and retention.

#Bio 

Dr. Hadi Gard (Charkhgard) is a tenured Associate Professor of Industrial and Management Systems Engineering and the founder and director of the Multi-Objective Optimization Laboratory at the University of South Florida (USF), where he has served since August 2016. Prior to joining USF, he was a postdoctoral research fellow at the Georgia Institute of Technology from August 2015 to August 2016. Dr. Gard has authored more than 58 articles in highly ranked journals, advancing all three pillars of Operations Research: theory, methodology, and applications. He is a leading expert in multi-objective optimization with a distinguished record of developing innovative optimization and AI techniques to address complex, real-world problems across a wide range of domains, including natural resource management, transportation,  healthcare, and energy. He is a member of the Tampa General Hospital Cancer Institute and the USF Chapter of the National Academy of Inventors. Dr. Gard's research has been funded by several U.S. federal agencies, including the National Science Foundation (NSF), the U.S. Environmental Protection Agency (EPA), and the U.S. Army Corps of Engineers, among others.