🤖 AI Summary
This work addresses the challenge of designing efficient and truthful incentive mechanisms in spatial crowdsourcing, where both task requesters and workers hold private valuations. To tackle this issue, the authors propose TRUST-SC, a novel framework that integrates spatial clustering, majority-vote-based quality assessment, and a multi-unit double auction mechanism. The approach first enhances system scalability through clustering, then identifies highly reliable workers via voting, and finally achieves task allocation and pricing through an incentive-compatible auction. Theoretical analysis and experimental evaluation demonstrate that TRUST-SC guarantees individual rationality and incentive compatibility while significantly outperforming existing baselines in terms of task allocation efficiency, accuracy of worker selection, and overall system performance.
📝 Abstract
Spatial crowdsourcing (SC) enables the assignment of location-based tasks to mobile users who must travel to specific locations to perform sensing or service activities. However, SC systems often operate in strategic environments where both task requesters and task executors possess private valuation information, posing challenges for designing efficient and truthful incentive mechanisms. To address these issues, this paper proposes a truthful multi-task double Auction for quality-aware spatial crowdsourcing (TRUST-SC). The proposed framework adopts a three-tier architecture. First, task executors are grouped into spatial clusters to improve scalability and reduce allocation complexity. Second, reliable executors are identified through a majority-voting-based quality evaluation process. Third, tasks are allocated, and payments are determined through a multi-unit double-auction mechanism that guarantees incentive compatibility and individual rationality. Theoretical analysis and simulation results demonstrate that the proposed mechanism achieves efficient task allocation, reliable executor selection, and improved performance compared with existing benchmark mechanisms.