Logo image
Model-based capacitated clustering with posterior regularization
Journal article   Peer reviewed

Model-based capacitated clustering with posterior regularization

Feng Mai, Michael J. Fry and Jeffrey W. Ohlmann
European journal of operational research, Vol.271(2), pp.594-605
12/01/2018
DOI: 10.1016/j.ejor.2018.04.048

View Online

Abstract

•We propose a new heuristic based on statistical models for the capacitated clustering problem.•We adapt the expectation-maximization algorithm using posterior regularization.•We evaluate its performance on deterministic test instances and a stochastic variant.•We investigate the impact of point patterns on clustering methods.•We study the performance of the algorithm using instances generated from a real-world dataset. We propose a heuristic approach to address the general class of optimization problems involving the capacitated clustering of observations consisting of variable values that are realizations from respective probability distributions. Based on the expectation-maximization algorithm, our approach unifies Gaussian mixture modeling for clustering analysis and cluster capacity constraints using a posterior regularization framework. To test our algorithm, we consider the capacitated p-median problem in which the observations consist of geographic locations of customers and the corresponding demand of these customers. Our heuristic has superior performance compared to classic geometrical clustering heuristics, with robust performance over a collection of instance types.
Capacitated p-median problem Expectation-maximization algorithm Gaussian mixture models Heuristics Posterior regularization

Details

Metrics

Logo image