Predicting Unsolvable Deals in the Birds of a Feather Solitaire Game

Abstract In this paper, we analyze Birds of a Feather (BoaF), a solitaire game played with 16 cards. While the large majority of deals are solvable, the set of unsolvable deals share certain characteristics that can be determined from the adjacency matrix of the corresponding “compatibility graph”. We create a binary decision tree based on just three variables to predict whether a given deal is solvable. Our predictive model, tested on 30,000 random deals, correctly classifies over 99.9% of our data.