CrewScout is an expert-team finding system based on the concept of skyline teams and efficient algorithms for finding such teams. Given a set of experts, CrewScout finds all k-expert skyline teams, which are not dominated by any other k-expert teams. The dominance between teams is governed by comparing their aggregated expertise vectors. The need for finding expert teams prevails in applications such as question answering, crowdsourcing, panel selection, and project team formation. CrewScout is an end-to-end system with an interactive user interface that assists users in choosing teams and an demonstration of its application domains.



Acknowledgement: This work is partially supported by NSF grant 0852674, 0915834, 1018865, 1117297, 1117369, 1343976, and 1408928. Additional support comes from Microsoft Research and the National Natural Science Foundation of China. Any opinions, findings, and conclusions or recommendations expressed in this work are those of the authors and do not necessarily reflect the views of the funding agencies.

Disclaimer: The Paper Review, Fantasy Basketball and StackOverflow QA datasets are collected from academic.research.microsoft.com, www.databasebasketball.com and data.stackexchange.com, respectively. None of these datasets are complete. Hence, the expertise score shown by CrewScout does not reflcet actual expertise of an expert.