Effective Bayesian Modeling of Groups of Related Count Time Series
This addresses forecasting challenges in domains like supply chain planning, but it is incremental as it builds on existing Bayesian methods for count data.
The paper tackles the problem of forecasting count time series by introducing a hierarchical Bayesian model that accounts for explanatory variables and shares statistical strength across groups, demonstrating its performance on supply chain planning datasets.
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.