Multiplayer online battle arena (MOBAs) games are one of the most popular types of online games. Annual tournaments draw large online viewership and reward the winning teams with large monetary prizes. Character selection prior to the start of the game (draft) plays a major role in the way the game is played and can give a large advantage to either team. Hence, professional teams try to maximize their winning chances by selecting the optimal team composition to counter their opponents. However, drafting is a complex process that requires deep game knowledge and preparation, which makes it stressful and error-prone. In this article, we present an automatic drafter system based on the suggestions of a discriminative neural network and evaluate how it performs on the MOBAs <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Heroes of the Storm (HotS)</i> and <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DOTA 2</i> . We propose a method to appropriately exploit very heterogeneous data sets that aggregates data from various versions of the games. Drafter testing on professional games shows that the actual selected hero was present in the top three determined by our drafting tool 30.4% of the time for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">HotS</i> and 17.6% for <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DOTA 2</i> . The performance obtained by this method exceeds all previously reported results.