Retail in High Definition: Monitoring Customer Assistance Through Video Analytics

Andres Musalem (), Marcelo Olivares () and Ariel Schilkrut ()
Additional contact information
Andres Musalem: Industrial Engineering Department, University of Chile and Instituto Sistemas Complejos de Ingeniería (ISCI), Santiago, Region Metropolitana 8370456, Chile
Marcelo Olivares: Industrial Engineering Department, University of Chile and Instituto Sistemas Complejos de Ingeniería (ISCI), Santiago, Region Metropolitana 8370456, Chile
Ariel Schilkrut: Zippedi, Burlingame, California 94010

Manufacturing & Service Operations Management, 2021, vol. 23, issue 5, 1025-1042

Abstract: Problem definition : We consider the development of an efficient and scalable video-analytics approach to measure customer assistance and its mediating role in the relationship between staffing levels and revenues. Academic/practical relevance : Staffing decisions account for a large portion of a retailer’s operational costs. Researchers have studied the extent to which an increase in staffing levels translates into greater revenues, without emphasizing the underlying mechanisms that generate this potential improvement, such as assisting customers. Methodology : We use econometric methods, including survival-analysis techniques, to analyze data gathered from in-store video recordings of customer visits to stores of a women’s apparel chain. Results : We find that, under average store conditions, a 25% increase in labor yields a 16% increase in store revenues. An increase in the assistance of customers while searching, browsing, or trying products mediates approximately 50% of this increase, while the remainder originates from other activities, such as helping customers at the checkout counter. Moreover, we find that this form of assistance has a significant and positive impact on both conversion and ticket size. Managerial implications : Our approach can be used to explain heterogeneity in employee productivity across stores, to monitor and detect unexpected deviations in customer-assistance levels, and to measure the productivity of multitasking agents for the different functions that they perform.

Keywords: empirical OM; service operations; marketing/OM interface; retail planning; OM practice; hazard models; staffing decisions; multitasking (search for similar items in EconPapers)
Date: 2021
References: Add references at CitEc
Citations:

Downloads: (external link)
http://dx.doi.org/10.1287/msom.2020.0865 (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:inm:ormsom:v:23:y:2021:i:5:p:1025-1042

Access Statistics for this article

More articles in Manufacturing & Service Operations Management from INFORMS Contact information at EDIRC.
Bibliographic data for series maintained by Chris Asher ().