Skip to main content
Research project

Forecasting and influencing product returns and fraud rates in a Covid-19 world

Project overview

Covid-19 has significantly aggravated the problem of high product returns rates, which have been increasing over the last few years. This is a significant challenge for retailers and society, causing economic, social and ecological harm. Returns lead to added complex processing, transportation and wasted resources, as many products cannot be resold and risk going to landfill.
Online shopping thrived during the lockdown, and many retailers extended their returns periods. A surge of product returns arrived when non-essential retailers reopened. Problems that are costly in normal periods (e.g. wardrobing, fraudulent refunds, serial returners) have become worse in this pandemic period. With recent research showing that many customers will retain their new online shopping habits, the problems will stay, too.

We conducted two consumer surveys, interviewed 9 retailers and 5 retail experts to improve our understanding of consumer behaviours in a pandemic. We then modelled this at micro and macro levels using explainable artificial intelligence (AI) techniques to forecast returns and fraud rates in a world dominated by Covid-19 conditions. To mitigate this, we developped a set of measures, indicating the expected effectiveness and environmental impact.
The ultimate goals are to help retailers operate efficiently and thrive in this challenging time, avoiding the need to cut jobs and thereby increasing the financial burden on welfare. This project will uniquely combine behavioural research with the development of explainable AI that retailers can use to mitigate the economic and ecological effects of product returns.


Other researchers

Gary Wills PhD, CEng, FHEA, MIET

Research interests

  • Internet of Things (IoT),
  • Data Protection,
  • Information Assurance,

Professor Enrico Gerding


Research interests

  • My main research focuses on applications where autonomous self-interested agents compete in markets and negotiate, and where designing appropriate incentives is important to ensure a well functioning and fair society. My research combines theory, mainly game theory and mechanism design, with practical applications. Specific applications include: autonomous vehicles, the smart grid, online advertising markets, cloud computing, algorithmic trading, ride sharing and data privacy.
  • I'm currently an investigator on the following projects:
  • AutoTrust: Human Centered Internet of Vehicles This EPSRC-funded platfrom grants looks at a wide range of aspects around the Connected and Autonomous Vehicles (CAVs), such as the interaction with autonomous systems (human-to-vehicle interaction), the issue of data privacy and consent, as well as the incentives and optimisation of e.g. traffic flow. Specific topics include: how do platoons form and how can they be used most effectively to improve traffic flow; how can we incentivise better use of public transport and/or shared vehicles (ride sharing); how can we best combine different modes of transport to reduce carbon emissions; how can we ensure that transportation data can be stored securely and used for research purposes; in autonomous vehicles and autonomous systems more generally, how can we reason about concepts such as responsibility and accountability especially when there is shared responsibility of a coalition (e.g. in case of a collision). 

Dr PK Senyo

Associate Professor

Research interests

  • Artificial Intelligence (AI)
  • Digital Transformation and Innovation
  • FinTech

Dr Steffen Bayer

Lecturer in Business Analytics

Research interests

  • Simulation Modelling
  • Health Systems Research
  • Health Planning

Collaborating research institutes, centres and groups

Research outputs

Danni Zhang,
Regina Frei,
& PK Senyo
, 2023 , Business Strategy and the Environment , 32 (7) , 4636--4661
Type: article
Danni Zhang,
Regina Frei,
P.K. Senyo,
& Adrian Beck
, 2022 , Journal of Retailing and Consumer Services , 70
Type: article
to top