Online labor markets, which allow applicants to seek suitable jobs anytime and anywhere, offer greater flexibility than traditional offline labor markets. This paper investigates a dynamic matching system that assigns appropriate applicants to appropriate vacancies in the condition that the arrivals of applicants and vacancies are uncertain. The objective of the matching system is to obtain a stable matching solution for both applicants and vacancies. To this aim, we propose three dynamic matching algorithms for three different market settings. The theoretical proof of the stability of each matching algorithm is given, and we conduct a series of computational experiments to verify the effectiveness and efficiency of the proposed matching algorithms. The results indicate that the algorithms can be an efficient and effective tool for recruitment management in today's active and internet-based labor markets to reduce the administrative workload of human resource departments and produce stable job allocations.

Shared mobility is an emerging urban logistics solution that aims to enhance transportation efficiency by leveraging underutilized transportation resources owned by individuals. In contrast to traditional urban logistics, the transportation resources are derived from self-employed individuals rather than company employees, rendering the design of appropriate matching mechanisms a pressing issue to be addressed. From this perspective, we have conducted a comprehensive review of the relevant literature and classified the literature based on information acquisition completeness. Our findings reveal that current research lacks analysis of the supply-side behavior, consideration of specific constraints in the shared mobility context, and performance evaluation of matching mechanisms in dynamic environments.

The efficiency of crowd-sourced delivery services (CDS) like UberEats and AmazonFlex highly depends on the decisions of individual shippers. Operating as freelancers, these shippers have the freedom to accept or decline orders from the CDS platform. Their decisions not only affect their earnings and the waiting times for orders but also influence the platforms’ overall revenue and reputation. Understanding the factors that shape these decisions is thus crucial. In our study, we gather data from CDS shippers in Shanghai, China, using stated preference surveys. We then design a discrete choice model to predict shippers’ behaviors and compare its accuracy, computational efficiency, and interpretability with five commonly used machine learning methods. Our analyses reveal that the Extreme Gradient Boosting (XGB) model and Random Forests (RFs) model outperform other models in prediction accuracy, achieving f1 scores of 69.3% and 65% respectively. Notably, our per- mutation importance analysis indicate that the shipper’s age, income, and the compensation awarded per order are the most influential determinants in their decision to accept or decline orders.