Understanding the characteristics of a "good" team and members diversity affects the outcomes group in a question of growing importance for the organizations, for their competitive advantage relies more and more on innovation, produced by virtual cooperation on knowledge production. In this study, we propose a method to forecast the future quality of an online knowledge production community ­or online epistemic community­ by studying the composition of the group who initiated them (the "core members" of, in this case, an article). First, we set a team building period which is defined as the period of 120 days after article creation in order to construct this "core members" group. Second, we explore the effects on article quality of both group and member diversity. Core members' characteristics are learned from their previous behavior. The analysis is based on the French Wikipedia project. Our results show that the most important attributes of initial core member to have a high quality article are average reputation, diversity's contribution, participation, and group size. We also find no significant effects of experience diversity and reputation during the team building period.