On Assigning Implicit Reputation Scores in an Online Labor Marketplace

In online labor marketplaces employers post job openings and receive applications by workers interested in them. The employers decide which applicant to hire and then they work with the selected worker to accomplish the job requirements. At the end of the contract, an employer can provide his worker with some rating that becomes visible in the online worker profile and can guide future hiring decisions of other employers. In this paper, we discuss some of the shortcomings of the existing reputation system and we propose a new reputation mechanism that combines employer implicit feedback signals in a link-analysis-based approach. The new system addresses the shortcomings of the existing one while yielding similar or better signal for the worker quality.