Practice Prize Report—Quantifying and Improving Promotion Effectiveness at CVS

Abstract

We quantified the net unit and profit impact of each promotion offered in 2003 by CVS, a leading U.S. drug retail chain, and analyzed the key drivers of variation in this net impact. We used this analysis to identify the least effective promotions and conducted a controlled field test to demonstrate the impact of eliminating them before chainwide implementation. Our key findings are as follows. First, approximately 45% of the gross lift from promotions is incremental for CVS. Further, for every unit of gross lift, 0.16 unit of some other product is purchased elsewhere in the store. Still, more than 50% of promotions are not profitable because the lower promotional margin is not sufficiently offset by incremental units. Second, there is substantial variation in net profit impact across categories. Our field test shows that eliminating promotions chainwide in 15 of the worst performing categories will decrease sales by about $7.8 million but will improve profit by approximately $52.6 million. This is very impressive given that CVS front store sales in 2003 were approximately $9 billion while the net profit impact of promotions was −$25.3 million.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 39 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.