As part of their design, card games often include information that is hidden from opponents and represents a strategic advantage if discovered. A player that can discover this information will be able to alter their strategy based on the nature of that information, and therefore become a more competent opponent. In this work, we employed association rule mining techniques for predicting item multisets, and showed them to be effective in predicting the content of Android: Netrunner decks. We then applied different modifications based on heuristic knowledge of the Android: Netrunner game, and showed the effectiveness of techniques which consider this knowledge during rule generation and prediction. The work is currently being extended to predict the content of opponent’s decks in Magic: The Gathering.