Probabilistic forecasting of heterogeneous consumer transaction-sales time series

TL;DR

This paper introduces a Bayesian methodology for multi-step ahead forecasting of supermarket sales, utilizing dynamic count mixture models and novel binary cascade models to improve accuracy and scalability across many items.

Contribution

It develops a scalable Bayesian framework with dynamic models and multi-scale information sharing for improved sales forecasting of heterogeneous consumer transactions.

Findings

Enhanced forecast accuracy demonstrated in case study

Effective incorporation of time-varying predictors

Scalable parallel filtering approach

Abstract

We present new Bayesian methodology for consumer sales forecasting. With a focus on multi-step ahead forecasting of daily sales of many supermarket items, we adapt dynamic count mixture models to forecast individual customer transactions, and introduce novel dynamic binary cascade models for predicting counts of items per transaction. These transactions-sales models can incorporate time-varying trend, seasonal, price, promotion, random effects and other outlet-specific predictors for individual items. Sequential Bayesian analysis involves fast, parallel filtering on sets of decoupled items and is adaptable across items that may exhibit widely varying characteristics. A multi-scale approach enables information sharing across items with related patterns over time to improve prediction while maintaining scalability to many items. A motivating case study in many-item, multi-period, multi-step ahead supermarket sales forecasting provides examples that demonstrate improved forecast accuracy in multiple metrics, and illustrates the benefits of full probabilistic models for forecast accuracy evaluation and comparison. Keywords: Bayesian forecasting; decouple/recouple; dynamic binary cascade; forecast calibration; intermittent demand; multi-scale forecasting; predicting rare events; sales per transaction; supermarket sales forecasting