Using customer-related data to enhance e-grocery home delivery
| Date | 16 October 2017 |
| DOI | https://doi.org/10.1108/IMDS-10-2016-0432 |
| Published date | 16 October 2017 |
| Pages | 1917-1933 |
| Author | Shenle Pan,Vaggelis Giannikas,Yufei Han,Etta Grover-Silva,Bin Qiao |
| Subject Matter | Information & knowledge management,Information systems,Data management systems,Knowledge management,Knowledge sharing,Management science & operations,Supply chain management,Supply chain information systems,Logistics,Quality management/systems |
Using customer-related data to
enhance e-grocery home delivery
Shenle Pan
CGS –Centre de Gestion Scientifique,
MINES ParisTech, PSL Research University, Paris, France
Vaggelis Giannikas
Institute for Manufacturing, University of Cambridge,
Cambridge, UK
Yufei Han
CGS –Centre de Gestion Scientifique,
MINES ParisTech, PSL Research University, Paris, France
Etta Grover-Silva
PERSEE –Centre for Process Energies and Energy Systems, MINES ParisTech,
PSL Research University, Sophia Antipolis, France, and
Bin Qiao
CGS –Centre de Gestion Scientifique,
MINES ParisTech, PSL Research University, Paris, France
Abstract
Purpose –The development of e-grocery allows people to purchase food online and benefit from home
delivery service. Nevertheless, a high rate of failed deliveries due to the customer’s absence causes significant
loss of logistics efficiency, especially for perishable food. The purpose of this paper is to propose an
innovative approach to use customer-related data to optimize e-grocery home delivery. The approach
estimates the absence probability of a customer by mining electricity consumption data, in order to improve
the success rate of delivery and optimize transportation.
Design/methodology/approach –The methodological approach consists of two stages: a data mining
stage that estimates absence probabilities, and an optimization stage to optimize transportation.
Findings –Computational experiments reveal that the proposed approach could reduce the total travel
distance by 3-20 percent, and theoretically increase the success rate of first-round delivery approximately
by18-26 percent.
Research limitations/implications –The proposed approach combines two attractive research streams
on data mining and transportation planning to provide a solution for e-commerce logistics.
Practical implications –This study gives an insight to e-grocery retailers and carriers on how to use
customer-related data to improve home delivery effectiveness and efficiency.
Social implications –The proposed approach can be used to reduce environmental footprint generated by
freight distribution in a city, and to improve customers’experience on online shopping.
Originality/value –Being an experimental study, this work demonstrates the effectiveness of data-driven
innovative solutions to e-grocery home delivery problem. The paper also provides a methodological approach
to this line of research.
Keywords Freight transportation, Home delivery, E-commerce, Data mining, City logistics,
Food delivery
Paper type Research paper
Industrial Management & Data
Systems
Vol. 117 No. 9, 2017
pp. 1917-1933
Emerald Publishing Limited
0263-5577
DOI 10.1108/IMDS-10-2016-0432
Received 14 October 2016
Revised 1 January 2017
17 February 2017
Accepted 22 February 2017
The current issue and full text archive of this journal is available on Emerald Insight at:
www.emeraldinsight.com/0263-5577.htm
© Shenle Pan, Vaggelis Giannikas, Yufei Han, Etta Grover-Silva and Bin Qiao. Published by Emerald
Publishing Limited. This article is published under the Creative Commons Attribution (CC BY 4.0)
licence. Anyone may reproduce, distribute, translate and create derivative works of this article
(for both commercial & non-commercial purposes), subject to full attribution to the original publication
and authors. The full terms of this licence may be seen at http://creativecommons.org/licences/by/4.0/
legalcode
1917
E-grocery
home delivery
1. Introduction
Recent developments of e-commerce have had a significant impact on food supply chains.
Today, many traditional grocery retailers offer their customers the opportunity to purchase
food items online and have them delivered to their home utilizing their existing distribution
network (Ogawara et al., 2003; Agatz et al., 2008). At the same time, new companies enter the
retail groceries market by providing online supermarkets with no physical stores, fulfilling
home deliveries from their warehouses (e.g. the case of Ocado, Saskia et al., 2016). In addition
to that, internet-based retailers, like Amazon, exploit their e-commerce expertise to build
their own online grocery shops thus extending even more the options end-customers have
for purchasing groceries online (Kang et al., 2016).
In e-grocery commerce, home delivery –the process of delivering goods from a
retailer’s storage point (e.g. distribution centers, shops) to a customer’shome–plays a
crucial role (Punakivi and Saranen, 2001). In fact, due to its convenience to customers,
home delivery has become a dominant distribution channel of business-to-consumer
e-commerce (Campbell and Savelsbergh, 2006). Nevertheless, a certain challenge faced in
e-grocery is that the perishability and storage condition-sensitivity of food and drink
items requires the attendance of the customer at the moment of delivery (Hsu et al., 2007).
At the same time, this makes alternative methods for unattended delivery, such as
delivery boxes, reception boxes and shared reception boxes, hard and unsafe to use.
This has led e-tailers to introduce strict policies for deliveries that could not be completed
due to the customer’s non-attendance (Ehmke, 2012a), while aiming to increase the
probability of an attended delivery by allowing their customers to choose their preferred
time slot. However, it is still common for end-customers to be absent at the time of
delivery either due to their own fault (e.g. failing to remember) or due to a delayed delivery
(e.g. due to traffic).
In this paper, we aim to address the attended home delivery problem (AHDP)
(Ehmke, 2012a; Ehmke and Campbell, 2014) in e-grocery motivated by the fact the
attendance of the customer is often hard to predict. We do this by investigating a new
approach that utilizes customer-related data to improve attended home delivery efficiency.
The approach consists of two stages. The first stage concerns a data mining process, whose
objective is to estimate the purchaser’s absence probability at a given time window
according to his/her electricity consumption behavior. The second stage uses the calculated
absence probabilities as an input to an optimization model for managing the fleet of trucks
that execute the home deliveries.
This paper aims to make both a theoretical and a practical contribution to the AHDP.
With regards to the theoretical contribution, this study is among the first ones applying data
mining techniques to AHDP. It provides a novel methodology to investigate the AHDP from
the aspect of customer-related data, which can be thought of as a new research line on
AHDP. From a practical point of view, the two-stage approach proposed could serve as a
decision-making model for e-grocery retailers, or other retail businesses that provide
(attended) home delivery service, to organize or enhance their delivery service.
Following this introduction, Section 2 provides a review of related work. Then, Section 3
presents the two-stage approach, that is, respectively, data mining stage and the
transportation planning stage. Section 4 presents an application example to demonstrate
the practicability and performance of the proposed approach. Finally Section 5 concludes
this work.
2. A brief review of e-grocery and its logistics
In this section, we briefly discuss the literature from three related problems:
current challenges to grocery and food e-commerce, delivering grocery and food items in
e-commerce, and innovations in home delivery.
1918
IMDS
117,9
To continue reading
Request your trial