Application of analytics in food retailing to improve online order picking time estimations

Abstract

Offering a good online grocery shopping service is becoming an increasingly crucial aspect for food retailers due to the highly competitive nature of this sector. To avoid large investments, many supermarket chains have adopted an in-store strategy, where online orders are picked in traditional stores. In order to successfully implement this omnichannel strategy, retailers need to plan shared organisational structures and methods correctly. The purpose of this study is to determine the extent to which certain characteristics of store and online orders influence the order picking time. Through an empirical analysis conducted in a Spanish e-grocer, a multiple linear regression model is proposed to estimate online order picking time. The research method proposed herein enables e-grocers to plan fulfilment operations, organise resources properly, and define and adjust their capacity to respond efficiently to market demand. We present an innovative research application that deeply integrates analytics into retail operations to improve industry practice and strengthen the theoretical foundation. Our contribution serves to support and evaluate the informed decision making process along the supply chain by optimising the use of resources and facilitating more efficient online order picking scheduling.