Effective Bayesian Modeling of Groups of Related Count Time Series
Machine Learning
2014-05-16 v1 Applications
Abstract
Time series of counts arise in a variety of forecasting applications, for which traditional models are generally inappropriate. This paper introduces a hierarchical Bayesian formulation applicable to count time series that can easily account for explanatory variables and share statistical strength across groups of related time series. We derive an efficient approximate inference technique, and illustrate its performance on a number of datasets from supply chain planning.
Keywords
Cite
@article{arxiv.1405.3738,
title = {Effective Bayesian Modeling of Groups of Related Count Time Series},
author = {Nicolas Chapados},
journal= {arXiv preprint arXiv:1405.3738},
year = {2014}
}
Comments
10 pages, 7 figures. Appears in Proceedings of the 31st International Conference on Machine Learning, Beijing, China, 2014. JMLR: W&CP volume 32