Predicting Drafted Deck Strength for "Magic: the Gathering"
2026-07-06 • Machine Learning
Machine LearningArtificial Intelligence
AI summaryⓘ
The authors looked at Draft, a mode in the card game Magic: the Gathering where players pick cards one by one from random packs to build a deck. This process is tricky because the available cards keep changing and affect how the game plays. They made a new model that understands the order of picks and the combination of cards to better predict how well a draft will go. Their approach works better than simpler models and helps study decision-making in this complex setting.
Magic: the GatheringDraft formatdeck-buildingpolicy learningcard embeddingscombinatorial synergyoutcome predictionmachine learningencoder modelpartial information
Authors
Tomas Rigaux, Hisashi Kashima
Abstract
Many real-world games do not admit a fixed, compact rule set: instead, their dynamics are defined by interactions among a large and often evolving collection of game pieces, making general-purpose policy learning impractical. Magic: the Gathering (MTG) exemplifies this setting, where the cards themselves define and alter gameplay rules, strategic constraints, and long-term outcomes, while the pool of available cards is ever-changing. We study Draft, a constrained deck-building format of MTG in which eight players make 39-45 sequential selections from semi-random packs to construct a 40-card deck under partial information. By isolating the card selection process from gameplay, Draft provides a tractable yet non-trivial setting for studying decision-making driven by combinatorial card synergies. We propose an encoder-based model that produces set-contextualized card embeddings to encode the draft decision sequence, with a consistent improvement over linear baselines on large-scale real-world data, establishing a first learned benchmark for outcome prediction in MTG Draft. Our code is available at github.com/akulen/MtGDraftEncoder.