Estimating Substitution and Basket Effects in Retail Stores: Implications for Assortment Planning

Vidya Mani, Douglas J. Thomas, Saurabh Bansal

Research output: Contribution to journalArticlepeer-review

2 Scopus citations

Abstract

Many retailers are reducing store footprint and downsizing their assortments accordingly to improve store productivity. Some of the revenue for items removed from the assortment may be recouped by substitution, but also some of the revenue for items kept in the assortment may be lost due to basket abandonment. For a practical setting where baskets may contain any subset of items from thousands of products, estimating both substitution and basket effects is a challenge. To address this, we develop a demand model that combines a multinomial logit (MNL) model to estimate substitution within a subcategory and a purchase-incidence model to estimate basket retention. Using transaction and product availability data from 12 stores of an office supplies retail chain that were dramatically downsized from large- to small-format stores, we show that (i) storewide basket effects are substantial (our model with basket effects predicts out-of-sample transactions with mean absolute percent error (MAPE) of only 7% compared with 22% for a model with only substitution effects), (ii) poor service level can significantly exacerbate lost profit due to abandoned baskets at these stores, and (iii) consideration of the basket effect in assortment selection for the small stores can significantly improve basket retention and increase profits (by up to 16%) at these stores.

Original languageEnglish (US)
Pages (from-to)5002-5024
Number of pages23
JournalManagement Science
Volume68
Issue number7
DOIs
StatePublished - Jul 2022

All Science Journal Classification (ASJC) codes

  • Strategy and Management
  • Management Science and Operations Research

Fingerprint

Dive into the research topics of 'Estimating Substitution and Basket Effects in Retail Stores: Implications for Assortment Planning'. Together they form a unique fingerprint.

Cite this