Why promotion strategies based on market basket analysis do not work

Authors:
Bernd Vindevogel;Dirk Van den Poel;Geert Wets
Affiliations:
Department of Marketing, Ghent University, Hoveniersberg 24, 9000 Ghent, Belgium;Department of Marketing, Ghent University, Hoveniersberg 24, 9000 Ghent, Belgium;Limburg University, Universitaire Campus Bld D, 3590 Diepenbeek, Belgium
Venue:
Expert Systems with Applications: An International Journal
Year:
2005

Citing 7
Cited 3

Beyond Market Baskets: Generalizing Association Rules to Dependence Rules

Data Mining and Knowledge Discovery
The "Shopping Basket": a Model for Multicategory Purchase Incidence Decisions

Marketing Science
The Category-Demand Effects of Price Promotions

Marketing Science
Modeling Consumer Demand for Variety

Marketing Science
Building an Association Rules Framework to Improve Product Assortment Decisions

Data Mining and Knowledge Discovery
Multiple Discreteness and Product Differentiation: Demand for Carbonated Soft Drinks

Marketing Science
Direct and indirect effects of retail promotions on sales and profits in the do-it-yourself market

Expert Systems with Applications: An International Journal

Electronic promotion to new customers using mkNN learning

Information Sciences: an International Journal
Grocery Product Recommendations from Natural Language Inputs

UMAP '09 Proceedings of the 17th International Conference on User Modeling, Adaptation, and Personalization: formerly UM and AH
A quantitative correlation coefficient mining method for business intelligence in small and medium enterprises of trading business

Expert Systems with Applications: An International Journal

Quantified Score

Hi-index	12.05

Visualization

Abstract

In text books as well as in the business literature, market basket analysis is often promoted as a means to obtain product associations to base a retailer's promotion strategy on. They argue that associated products with a high lift/interest can be promoted effectively by only discounting just one of the two products. Implicitly, they argue that market basket analysis automatically identifies complements. In this research, we show that this implicit assumption does not hold. Our empirical analysis reveals that market basket analysis identifies as many substitutes as complements. Therefore, market basket analysis cannot be used to build a promotion expert system for retailers. Instead, we advice to base the promotion strategy on cross-price elasticities. We conduct this research using scanner data of a large European retailer. Multivariate time-series techniques are used to identify both short-run as well as long-run (persistent) effects of promotions.