A0569
Title: Dynamic Bayesian networks with conditional dynamics in edge addition and deletion
Authors: Shun Hin Chan - The Hong Kong University of Science and Technology (Hong Kong)
Amanda Chu - The Education University of Hong Kong (China)
Mike So - The Hong Kong University of Science and Technology (Hong Kong) [presenting]
Abstract: A dynamic Bayesian network framework is presented that facilitates intuitive gradual edge changes. Two conditional dynamics are used to model the edge addition and deletion, as well as edge selection separately. Unlike previous research that uses a mixture network approach, which restricts the number of possible edge changes or structural priors to induce gradual changes, which can lead to unclear network evolution, the model induces more frequent and intuitive edge change dynamics. Markov chain Monte Carlo (MCMC) sampling is employed to estimate the model structures and parameters and demonstrate the model's effectiveness in a portfolio selection application.
