ABSTRACT
Market basket analysis (MBA), or the mining of transactional data to uncover association rules, is a popular methodology used in managerial decision making. MBA is centered around three key parameters: support, confidence, and lift, and the choice of starting values for these parameters can have a significant impact on the results of the analysis. We develop a procedure in R around the Apriori algorithm to help in identifying lift maximising rules when the support covers a specified proportion. The procedure facilitates the choice of minimum parameters, eliminates redundancies, and organizes the resulting association rules into actionable formats. When applied to the US auto repair data, we find un-exploited bundling packages that can be added to the scheduled maintenance services of traditional marketing campaigns.
Acknowledgments
The authors would like to thank David Sommers and Ranjhana Rama-Subramanian for their comments on previous drafts and insights.
Disclosure statement
On behalf of all authors, the corresponding author states that there is no conflict of interest.
Notes
1. A very useful review of the main elements of market basket analysis can be found in the R tutorials: www.datacamp.com/community/tutorials/market-basket-analysis-r.
2. For reviews of multiple MBA algorithms, we recommend Tan et al. (Citation2018), Arora et al. (Citation2013), and Cavique (Citation2007) and the literature cited therein.
3. The actual code is available to readers upon an email request.