A forecasting analytics model for assessing forecast error in e-fulfilment performance
| DOI | https://doi.org/10.1108/IMDS-01-2022-0056 |
| Published date | 31 August 2022 |
| Date | 31 August 2022 |
| Pages | 2583-2608 |
| 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 |
| Author | G.T.S. Ho,S.K. Choy,P.H. Tong,V. Tang |
A forecasting analytics model
for assessing forecast error in
e-fulfilment performance
G.T.S. Ho
Department of Supply Chain and Information Management,
The Hang Seng University of Hong Kong, Shatin, Hong Kong
S.K. Choy
Department of Mathematics Statistics and Insurance,
The Hang Seng University of Hong Kong, Shatin, Hong Kong, and
P.H. Tong and V. Tang
Department of Supply Chain and Information Management,
The Hang Seng University of Hong Kong, Shatin, Hong Kong
Abstract
Purpose –Demand forecast methodologies have been studied extensively to improve operations in
e-commerce. However, every forecast inevitably contains errors, and this may result in a disproportionate
impact on operations, particularly in the dynamic nature of fulfilling orders in e-commerce. This paper aims to
quantify the impact that forecast error in order demand has on order picking, the most costly and complex
operations in e-order fulfilment, in order to enhance the application of the demand forecast in an e-fulfilment
centre.
Design/methodology/approach –The paper presents a Gaussian regression based mathematical method
that translates the error of forecast accuracy in order demand to the performance fluctuations in e-order
fulfilment. In addition, the impact under distinct order picking methodologies, namely order batching and wave
picking. As described.
Findings –A structured model is developed to evaluate the impact of demand forecast error in order picking
performance. The findings in terms of global results and local distribution have important implications for
organizational decision-making in both long-term strategic planning and short-term daily workforce planning.
Originality/value –Earlier research examined demand forecasting methodologies in warehouse operations.
And order picking and examining the impact of error in demand forecasting on order picking operations has
been identified as a research gap. This paper contributes to closing this research gap by presenting a
mathematical model that quantifies impact of demand forecast error into fluctuations in order picking
performance.
Keywords Demand forecasting, Forecast error, Warehouse operations, Order picking
Paper type Research paper
1. Introduction
The e-commerce business is rapidly expanding around the globe and has an increasing
importance in our daily lives. A recent survey by the Centre for Retail Research (2020)
shows that the online retail market as a share of total retail trade essentially doubled between
2012 and 2019 in Europe and the United States, rising from 9.7% to 16.5% in the United States
and 4.8%–10.1% in Europe. To satisfy and retain customers, offering superior service
quality is a major component of e-commerce. A survey by Nisar and Prabhakar (2017) showed
a positive correlation between service quality and customer retention. This is reflected in
Assessing
forecast error
2583
The authors would like to thank the Research Grants Council of Hong Kong for supporting this research
under the Grant UGC/FDS14/E06/19. Also, this project is also supported partially by the Big Data
Intelligence Centre in The Hang Seng University of Hong Kong.
The current issue and full text archive of this journal is available on Emerald Insight at:
https://www.emerald.com/insight/0263-5577.htm
Received 7 February 2022
Revised 21 June 2022
11 August 2022
Accepted 13 August 2022
Industrial Management & Data
Systems
Vol. 122 No. 11, 2022
pp. 2583-2608
© Emerald Publishing Limited
0263-5577
DOI 10.1108/IMDS-01-2022-0056
the increasingly customer-centric design of supply chains (Christopher, 2016). In practice,
customers are often guaranteed in advance that they can receive items before a specified date
or within a selected time slot, with delivery charges often refunded should the delivery fail to
reach the customer in time (Leung et al., 2019). Such a customer-centric business model cannot
function without an efficiently managed warehouse that can handle subsequent order
fulfilment procedures such as order picking and last mile delivery. In addition, orders from e-
commerce are more irregular, fragmented and more difficult to predict, which vastly
increases the complexity and cost for completing an e-order.
Logistic Service Providers (LSPs) have faced new challenges during the coronavirus
(COVID-19) pandemic, where they experienced unprecedented demand and stress on e-order-
fulfilment operations. With cases still high and vaccines in short supply, many countries
impose restrictions in periods of lockdown to slow the spread of the virus. Consequently,
COVID-19 changes the shopping behaviour of customers who prefer to use online shopping,
such as groceries, toiletries, and dietary staples. In the United States, online food shopping
has jumped from 3 to 4% in usual times to 10–15% during the pandemic (Grashuis et al.,
2020). Similar results have been found in a recent survey ins China, where the percentage of
respondents who bought food and other necessities online increased from 11% to 38%.
However, despite facing increasing e-orders demand, to comply with social distancing
regulations from governments and prevent the spread of COVID-19, LSPs need to reallocate
and limit the workforce as well as the number of workers in e-fulfilment centres. This leads to
long processing and delivery times for customers, resulting in poor service satisfaction
(Chang and Meyerhoefer, 2021). Consequently, researchers have identified the most required
professional and fundamental logistics competences to provide general recommendations for
improvement in the relevant field. Cveti
cet al. (2017) concludes that performance
management and demand forecasting as amongst the most required professional
competencies of a logistics and supply chain management.
To facilitate resource planning in e-order fulfilment centres, demand forecasting and
determining staffing requirements are identified as major areas of focus (Defraeye and Van
Nieuwenhuyse, 2016). Recent research related to dem and forecasting has attract ed
significant attention in the e-commerce industry to improve warehouse operation
performance and resource planning (Van Gils et al., 2017;Leung et al., 2018). Methods
include time series forecasting, genetic algorithms, and machine learning. Demand forecasts
allow logistics practitioners to determine the workload of order picking operation and allocate
pickers accordingly. Insufficient allocation of pickers increases lead time, labour cost and
leads to potentially failing to meet business goals. Whereas an over-allocation of pickers
would resulting in higher cost, leading to low efficiency. An error in demand forecast, whether
it is an overestimation or underestimation of orders, would yield differing workload, and
could require different number of pickers for effective operation. Hence, a lack of
understanding in the impact of demand forecast error could lead to a mismatch of pickers
and workload, leading to poor performance or efficiency. Forecasting accuracy and its
relationship with warehouse operation performance has been identified as an important area
of research, but currently has been under-researched.
This issue is especially important in the e-commerce scenario, as the tight delivery
schedule requires practitioners to consolidate and pick items from storage quickly and
efficiently. Solving the optimal route for order picking is a Nondeterministic Polynomial-time
hard (NP-hard) problem (Armenzoni et al., 2017) and the route solution is highly sensitive to
initial changes. This means that assigning workers based purely on predicted total demand
may result in inconsistent performance, even assuming perfect prediction. The problem in
order picking is of great concern as it is often a bottleneck for the order fulfilment process and
has long been identified as one of the costliest components in running a warehouse (De Koster
et al., 2007. Therefore, it is of vital importance that the link between demand forecast,
IMDS
122,11
2584
To continue reading
Request your trial