|Saturday, February 25|
|CS18 Going Mainstream: Emerging Modeling Methods||
Sat, Feb 25, 9:15 AM - 10:45 AM
River Terrace 3
Amazon Product Co-Purchasing Network Estimation Through ERGM Model Using Reference Prior (303355)*Sayan Chakraborty, Michigan State University
Tapabrata Maiti, Michigan State University
Keywords: Social Networks, Exponential Random Graph Model, Reference Prior, MCMC, Tie-no-Tie
Network models are widely used to represent relations between actors or nodes. Recent studies on the network literature and graph model revealed various characteristics of the actors and how it influences the characteristics of it's neighboring actors. This work is motivated to formulate a large network through the Exponential Random Graph Model and apply a Bayesian approach through the reference prior technique to control the sensitivity of the inference and to get the maximized information from the model. We consider a large "Amazon product co-purchasing network" (Customers who bought this item also bought) and the purpose is to show how the blend of Exponential Random Graph Model and Bayesian techniques efficiently handles the estimation procedure through very fast computation and provides an efficient structural knowledge.