Mixed-Membership Stochastic Block-Models for Transactional Networks

Understand

Transactional network data can be thought of as a list of one-to-many communications(e.g., email) between nodes in a social network.

• Most social network models convert this type of data into binary relations between pairs of nodes.
• We develop a latent mixed membership model capable of modeling richer forms of transactional network data, including relations between more than two nodes.
• The model can cluster nodes and predict transactions.