The team formation problem has existed for many years in various guises. One important problem in the team formation problem is to produce small teams that have a required set of skills. We propose a framework that incorporates machine learning to predict unobserved links between collaborators, alongside improved Steiner tree problems to form small teams to cover given tasks. Our framework not only considers size of the team but also how likely are team members going to collaborate with each other. The results show that this model consistently returns smaller collaborative teams.
The team formation problem has existed for many years in various guises. One important challenge in the team formation problem is to produce small teams that have a required set of skills. We propose a framework that incorporates machine learning to augment a collaboration graph with latent links between collaborators. This is combined with the solution of Steiner tree problems to form small teams that cover a specified set of tasks. Our framework not only considers the size of the team but also the likelihood that team members are going to collaborate with each other. We demonstrate our results using data from the US Patent office covering two different companies' inventor networks. The results show that this technique can reduce the size of suggested teams.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.