Online Program Home
My Program

Abstract Details

Activity Number: 68
Type: Topic Contributed
Date/Time: Sunday, July 31, 2016 : 4:00 PM to 5:50 PM
Sponsor: Section on Bayesian Statistical Science
Abstract #318730 View Presentation
Title: Bayesian Dynamic Modeling and Analysis of Streaming Network Data
Author(s): Xi Chen* and Kaoru Irie and David Banks and Robert Haslinger and Jewell Thomas and Mike West
Companies: Duke University and Duke University and Duke University and MaxPoint and MaxPoint and Duke University
Keywords: Bayesian model emulation ; Dynamic network flow ; Gravity model ; Internet traffic flows ; On-line advertising ; Parallel computing

Traffic flow count data in networks arise in many applications, such as automobile or aviation transportation, certain directed social network contexts, and internet studies. Using an example of internet browser traffic flow through domains within a popular international news website, this paper presents Bayesian analyses of two linked models which, in tandem, allow fast, scalable and interpretable Bayesian inference. The first model is a flexible, non-stationary and non-Gaussian state-space model for streaming count data, able to adaptively characterize and quantify network dynamics effectively and efficiently in real-time. The second model is a time-varying gravity model that allows for closer and formal dissection of network dynamics. The former is fast and scalable, and maps to the second in a computationally trivial way to allow and interpret inferences on traffic flow characteristics, and on interactions among network nodes in particular.

Authors who are presenting talks have a * after their name.

Back to the full JSM 2016 program

Copyright © American Statistical Association