Winner Determination in Huge Elections with MapReduce

In computational social choice, we are concerned with the development of methods for joint decision making. A central problem in this field is the winner determination problem, which aims at identifying the most preferred alternative(s). With the rise of modern e-business platforms, processing of huge amounts of preference data has become an issue. In this work, we apply the MapReduce framework – which has been specifically designed for dealing with big data – to various versions of the winner determination problem. Our main result are efficient and highly parallel algorithms together with a performance analysis for this problem.