CrowdPick: A Generic Framework for Delivering Service Specific Crowd Infrastructure
Shahid Noor, Yasser Karim, Mahmud Hossain, Ragib Hasan · 2020
Crowdsourcing is an efficient and scalable way for the service providers (SP) to provide a broad range of services with a low initial service setup cost. With its growing popularity, people are continuously introducing new crowdsourcing-based applications and searching for suitable crowd platforms for the deployment of those applications as a service. Consequently, a contributor participates in multiple platforms from different SPs and concurrently executes various tasks in a time interval. As the number of SP increases, managing and monitoring each contributor separately becomes a primary challenge for each SP. Moreover, upgrading a service, ensuring service scalability, and migration is tough for any crowd-based service provider. Frequently, a service provider has difficulty finding the appropriate contributors that will satisfy their service specifications. Besides, as a contributor, it is also hard to decide whether or not they should participate in a task offered by an SP. Therefore, in this paper, we introduced CrowdPick, a middleware that provides a crowdsourced platform for the people who want to provide a crowdsourcing-based service. Each SP contacts CrowdPick for initiating any service chooses an appropriate application package from its repository and specifies its service requirements. Instead of joining individually to each SP, the contributor needs to register into CrowdPick. All the tasks associated with services are scheduled and monitored by CrowdPick, and the CrowdPick decides the corresponding monetary incentives. Along with providing a detailed cost-benefit analysis of an SP and a contributor, we describe the service level agreement (SLA) policies. We simulate our model to show that implementing CrowdPick in real life is viable, and beneficial for both an SP and a contributor.