Human-Computer Interactions in Demand Forecasting and Labor Scheduling Decisions

39 Pages Posted: 11 Dec 2022

See all articles by Caleb Kwon

Caleb Kwon

Harvard University - Technology & Operations Management Unit

Ananth Raman

Harvard University - Technology & Operations Management Unit

Jorge Tamayo

Harvard University - Business School (HBS)

Date Written: December 7, 2022

Abstract

We empirically analyze how managerial overrides to a commercial algorithm that forecasts demand and schedules labor affect store performance. We analyze administrative data from a large grocery retailer that utilizes a commercial algorithm to forecast demand and schedule labor across all their stores. In total, this data encompasses 29 million shifts covering 50,000 employees in more than 500 stores, totaling more than 800,000 store-date observations. Using an instrumental variables strategy that exploits exogenous events where the algorithm requires human intervention, we find that managerial overrides made to aggregate labor minutes and employee teams increase store performance. We make the broader point that exercising discretion based on private knowledge about demand and employee relationships is one channel by which managers add value to their stores.

Suggested Citation

Kwon, Caleb and Raman, Ananth and Tamayo, Jorge A., Human-Computer Interactions in Demand Forecasting and Labor Scheduling Decisions (December 7, 2022). Available at SSRN: https://ssrn.com/abstract=4296344 or http://dx.doi.org/10.2139/ssrn.4296344

Caleb Kwon (Contact Author)

Harvard University - Technology & Operations Management Unit ( email )

Boston, MA 02163
United States

Ananth Raman

Harvard University - Technology & Operations Management Unit ( email )

Boston, MA 02163
United States
617-495-6937 (Phone)
617-496-4059 (Fax)

Jorge A. Tamayo

Harvard University - Business School (HBS) ( email )

Soldiers Field Road
Morgan 270C
Boston, MA 02163
United States

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
65
Abstract Views
247
Rank
509,580
PlumX Metrics