Given an event O and a set of experts E, we describe a method for finding a subset of experts S whose aggregated opinions best predict the outcome of O. Therefore, the problem can be regarded as team formation for performing a prediction task. In order to estimate competency of each team we propose measure Sum Squared Error which uses experts’ records of predictions during past k days. For simplicity, opinion pooling is selected as the method of information aggregation. We prove in case of simple averaging of opinions, finding best team is NP-hard. We suggest some rounding and heuristic algorithms for finding near optimal solutions. Simulation results show that a variation of Tabu search used for solving maximum clique, works effectively for team selection problem.