Effective Bayesian Modeling of Groups of Related Count Time Series

TL;DR

This paper presents a hierarchical Bayesian model for count time series that incorporates explanatory variables and shares information across related groups, with an efficient inference method demonstrated on supply chain datasets.

Contribution

It introduces a novel hierarchical Bayesian framework for count time series that improves modeling flexibility and inference efficiency.

Findings

Effective modeling of count time series with explanatory variables.

Shared statistical strength improves forecasting accuracy.

Demonstrated superior performance on supply chain datasets.

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.