Incentivizing Sequential Crowdsourcing Systems

A crowdsourcing system such as Amazon's Mechanical Turk allows a crowdsource campaign initiator to recruit a large number of workers to accomplish a task. The proper design of such a crowdsourcing system becomes very challenging when the task involves multiple interdependent micro-tasks, and the initiator wants the task to be completed with the minimal cost and a high probability of success. In this paper, we address this challenge by designing an EI (Effort Incentivization) mechanism, which utilizes the peer effect to incentivize workers to act according to the initiator's best interest. We prove that EI is Bayesian incentive compatible and Bayesian individually rational. Our analysis shows that when there are multiple sequential interdependent micro-tasks, the initiator should provide higher rewards to those workers responsible for completing later stage micro-tasks. When there is a flexibility regarding the worker assignment to each micro-task, the initiator should assign fewer workers to later stage micro-tasks to minimize the initiator's overall payment. Numerical results show that our proposed EI mechanism can reduce the initiator's total payment by more than 70%, compared to a fixed reward mechanism. By optimizing the numbers of workers assigned to different interdependent micro-tasks, the initiator can reduce the total payment by up to 50% compared to a random assignment scheme.