Data mining for prediction of moves of professional poker players: An experimental approach

With the growing interest in research in poker, by scientists belonging to the area of Artificial Intelligence, has arisen the need to overcome the imperfect information of the same, as a stochastic game, by the challenges that this enables. In this work we intend to create data models that allow us to know the plays of a real player, supporting the decision to play in the pre-flop phase, within the Texas Hold'em side. To accomplish this, several Data Mining techniques were applied for classification, using RapidMiner software. The development of this work was based on data from online games of professional poker players, who had important information of the factors inherent to a real game.