Home » Internship

Isolation and Exclusion in a Social Distancing COVID-19 World

Isolation and Exclusion in a Social Distancing COVID-19 World

CDRC Data Scientist Intern, Rosalind Martin, working with Professor Susan Grant-Muller, Professor Alison Heppenstall and Dr Vikki Houlden from the University of Leeds, and Professor Rachel Franklin from the University of Newcastle, has produced a dashboard that identifies geographical areas which might experience increased isolation and exclusion as we leave the COVID-19 pandemic and lockdowns.

Project overview

Although much work has already been completed which identifies individuals most at risk from health impacts of the COVID-19 pandemic, there is considerable uncertainty regarding which societal impacts will persist as the UK leaves COVID-19 lockdowns. This project was undertaken with the aim of advancing the understanding of the social and spatial impacts of emergence from lockdown, particularly understanding how previously implemented restrictions will have impacted individuals and households. Using SPENSER, a synthetic population, we have identified individuals and households at risk from five COVID-19 restrictions: shielding, school closures, limited household interaction, furlough and limited to local area, along with households at risk from unique combinations of these five scenarios. This has been translated onto a dashboard which displays additive counts of household level impacts at the Middle Layer Super Output Area (MSOA) level.

Data and methods

We applied five COVID-19 restrictions (that cover a breadth of socio-economic impacts) to individuals and households across Yorkshire and the Humber. Our population came from SPENSER, a synthetic micro-population, along with additional characteristics obtained from supplementary datasets. The criteria for an individual or household to be impacted by each restriction were influenced by external statistics and are as follows:

Shielding: a randomly extracted 4.83% of the population who had been classified as in poor health, based on answering that their day-to-day activities were limited a lot due to a long-term health problem or disability in the 2011 census. The ailing population is representative of MSOA level trends and split into four age categories (0-15, 16-49, 50-64 and 65 and over).

School closure: households with at least one child aged 13 or under. This age was chosen as it is the age cut-off for forming a COVID-19 ‘childcare bubble’.

Limited household interaction: all single-person households as determined by a household size of one (a pre-existing characteristic in the SPENSER data).

Furlough: the proportion of individuals working in (1) Accommodation and food service activities, (2) Arts, entertainment and recreation, and other service activities and (3) Wholesale and retail trade, repair of motor vehicles and motorcycles industries, were identified at the MSOA level from 2011 census data and replicated proportionally in our SPENSER population. The average percentage of furloughed employees was then identified. These were 61.3%, 67% and 13.8% respectively.

Limited to local area: all households who live in an MSOA where there is no accessible green space within 1km. These data were from CDRC’s Access to Healthy Assets and Hazards dataset.

Once all the restrictions had been applied to the households, each household was assigned to a scenario which represented a unique combination of all of the five restrictions. There were 32 scenarios in total. This enabled additive counts of impacts on households to be calculated. These final outputs are displayed on the accompanying dashboard. Counts of household impacts are displayed alongside total household counts for each MSOA and Indices of Economic Insecurity, produced by Smith et al. (2020) and used with permission.

Front page of the Isolation and Exclusion dashboard

Key findings

This project has resulted in the development of an interactive dashboard, showing counts of household-level impacts at the MSOA level for Yorkshire and the Humber. Although patterns of household-level impacts are difficult to see from these maps, this work has explored how to use proxy data in order to identify individual- and household-level impacts from COVID-19 restrictions, and begun to unpack the complexities of combining data at the household level. This is something that must continue going forward as academics and policy makers continue to face the challenges that accompany understanding the social and spatial impacts of the emergence from lockdown.

Through this work, it has become apparent that certain COVID-19 specific datasets do not exist yet (such as the uptake of ‘support bubbles’) so assumptions have to be made on the extent of impacts. This detail should be added in to future tools when possible. Where data do exist, they are often lacking spatial resolution and so it has to be assumed that patterns have coarse geographies. This detail should be added in to future predictions when possible. Going forward, work must utilise more specific and detailed datasets.

The use of SPENSER as a micro-population has been foundational to understanding the impact of restrictions on individuals and households. It is recommended that any work going forward on this matter also uses small area population data as without it, any patterns of social and spatial impacts of emergence from lockdown will be coarse from the start.

Value of the research

The COVID-19 pandemic, with its associated lockdowns and restrictions, has brought vast change to the routines of families across the world. This work has had a small part in deciphering what these changes could mean for those across Yorkshire and the Humber. Dashboards with mapping have shown to be an important tool for understanding how health impacts of COVID-19 are distributed, this same logic applies to how lockdown restrictions combine spatially.

The dashboard can be found at: https://isolationpostcovid.azurewebsites.net/


  • COVID-19 causes health, social and economic impacts
  • Creation of a dashboard that displays different flavours of lockdowns
  • Supports pre-existing conclusions regarding the impact of COVID-19 lockdowns
  • Interrogation of complex layers of information aids policy reform
  • Current data are insufficient to capture COVID-19 lockdown impacts

Research themes

  • Urban Analytics
  • COVID-19
  • Spatial Inequality
  • Interactive Visualisation


Rosalind Martin, Data Scientist Intern at LIDA/CDRC

Professor Rachel Franklin, Professor of Geographical Analysis at the University of Newcastle

Professor Susan Grant-Muller, Chair in Technologies and Informatics at the University of Leeds

Professor Alison Heppenstall, Professor in Geocomputation at the University of Leeds

Dr Vikki Houlden, Lecturer in Urban Data Science at the University of Leeds


Consumer Data Research Centre (CDRC)


This project was funded by the Consumer Data Research Centre.

Funding for SPENSER is provided by The Alan Turing Institute, project reference R-LEE-004.


Smith, D., Moon, G. and Roderick, P. 2020. Indices of Economic Insecurity: Version 2, August 2020. GeoData Institute, University of Southampton. [Online]. [Accessed 18th March 2020. Available from: https://www.mylocalmap.org.uk/iaahealth/

Being A Data Science Intern

Photo of Rosalind Martin outdoors wearing a blue coat and a scarf

Being A Data Science Intern – insights, challenges and benefits

Rosalind is one of the Leeds Institute for Data Analytics’s (LIDA) current Data Scientist Interns, with a background in Geography (BSc) and Geographical Information Systems (GIS MSc).

I’ve always been a fan of physical geography, but as module choices expanded throughout my degrees I was increasingly drawn to (spatial) data modules. I love using GIS and coding to solve big data challenges.

My internship has been made up of two six-month projects, both funded by the Consumer Data Research Centre (CDRC). My first project was titled ‘Isolation and Exclusion in a Social Distancing Covid World’. Here, I worked under the supervision of academics from the Universities of Newcastle and Leeds, aiming to identify people and households at risk of isolation and exclusion as a result of Covid lockdown rules.

Photo of Rosalind Martin outdoors wearing a blue coat and a scarf

My second project is in the world of nutrition where I’m working closely with Leeds academics, Dr Michelle Morris and Vicki Jenneson, and a retail partner. I am designing an open access tool which will assist retailers in implementing new policy restricting the promotion of foods that are high in fat, salt and sugar – a crucial part of reducing obesity in the UK.

What has been my experience of the LIDA Internship Programme?

Aerial view of desk with hands over a laptop keyboard, pot plant, glasses and pen

As I’m sure many people would echo, the Covid pandemic has placed our jobs in unfamiliar situations. The reality of this internship being my first full-time post means that I’ve not been comparing my days to ways I have worked in the past. Instead, my experience has been shaped by remote team working with virtual training, coffee breaks and meetings. Although working from home (WFH) comes with its own challenges and complexities, I believe this has given me the capacity to be thankful to work on engaging projects rather than pining for something I used to have!

Due to the pandemic, many interns have been able to experience otherwise inaccessible conferences and workshops as they’ve transitioned online. I’ve been to events held by The Alan Turing Institute, the Royal Society, CDRC and more! Working as a remote cohort, the interns have set up coffee breaks and a weekly “pub” session to replicate those water-cooler conversations, lost due to WFH. This space allows us to talk about our projects, seek help from others who have different skillsets and to simply get to know each other.

What have I been proud to have accomplished so far on the internship?

Coding while WFH has been a true test of my perseverance. In the absence of spinning my chair around to ask for a fresh pair of eyes, I’ve really had to learn how to use documentation and online forums to navigate my coding challenges. I’ve also learnt how best to send questions (with reproducible examples) to other interns or my supervisors. I’ve seen a visible increase in my confidence and ability between my first and second projects, and I know this skill will continue to serve me in future careers. 

What are my quick hacks for getting the most out of the internship?

  • Obtaining data always takes longer than you think: be proactive in learning methods, using dummy data and reading around the subject while you wait
  • Talk to the interns: each intern has a different background and therefore their own unique combination of skills. Ask questions and be ready to offer your own experiences if asked
  • Write detailed descriptions of your GitHub commits: your future self will thank you when you return from Annual Leave to find you have a detailed record of what you were working on before you left for your holiday

How has working with the Consumer Data Research Centre (CDRC) helped with the delivery of my first project?

My first intern project aimed to identify those at risk of isolation and exclusion under Covid lockdown rules. In order to make detailed predictions of impacted individuals and households, I worked with a micro-simulated synthetic population called SPENSER. This CDRC and Alan Turing Institute funded project was essential for me to make predications at the household level. I also used other datasets to support my work including CDRC’s Access to Healthy Assets and Hazards dataset. The availability of these datasets enabled me to explore the Covid restrictions that were thought to negatively impact an individual’s risk of isolation.

How will this Internship help me progress my career in data science?

I have learnt more of the mechanics of data access throughout both of my projects – ranging from obtaining freely-available through to applying for safeguarded datasets (including how long the process can sometimes take!). In my projects, I have had the opportunity to talk to the City Council, UK and international universities, not-for-profit organisations and retailers. Speaking to people in a wide range of data roles has helped me to better understand the opportunities available in data science, and how roles interact with non-data scientists. 

Why would I recommend the LIDA Data Science Internship?

The LIDA Data Science Internship has given me the opportunity to own the delivery of two data science projects situated in very different subject areas. This has really expanded my understanding of how data can be used to solve very complex but nationally topical challenges. Owning the delivery of the projects as someone straight out of their Master’s has been a challenge, but I have been well supported by experienced supervisors and the extended LIDA network. With the breadth of internship projects and collaborators available across and in partnership with LIDA, the internship is the place to be!

LIDA is currently recruiting for its next cohort of Data Scientist Interns, due to start at the end of September 2021, with several projects taking place within the CDRC. Click here for more information and to apply.

Celebrating collaboration: the CDRC Masters Dissertation Scheme

Celebrating collaboration: the CDRC Masters Dissertation Scheme

Celebrating collaboration: the CDRC Masters Dissertation Scheme. Thursday 29th April 2021, 10:30-15:00.

The CDRC Masters Dissertation Scheme, now in its tenth year, has been successfully run by the Consumer Data Research Centre for the last seven years. The event celebrated the success of the scheme, and explored the changing nature of academic-industry collaboration. Masters students who had gone through the scheme presented project case studies, and a selection of alumni spoke of the positive impact the scheme had had on their data science careers. A panel session rounded off the event with a discussion of the possibilities and ambitions for the next seven years of the Masters Dissertation Scheme. The event was attended by industry partners, MDS alumni, and the CDRC team including Paul Longley, Alex Singleton, and Jonathan Reynolds.

Speaker biographies


1030-1130: The Business of Engagement. Session recording (Longley 0:06, Dugmore 7:05, Reynolds 28:27, Squires 41:21)

  • Introduction & welcome: Professor Paul Longley, Director, CDRC
  • The evolution of academic-industry collaboration: Keith Dugmore, Demographic Decisions. Slides
  • CDRC: Where are they now? MDS 7 years on: Dr Jonathan Reynolds, Deputy Director (Oxford), CDRC. Slides
  • The business of engagement: the firm’s perspective: Martin Squires, Director of Advanced Analytics, Pets at Home. Slides

1145-1245: Alumni presentations. Session recording (Murage 2:16, Davies 25:10, Tonge & Montt 45:53)

  • Nombuyiselo Murage, Tamoco. Dissertation at Tamoco. MSc Geographic Data Science, University of Liverpool. Slides
  • Alec Davies, Pets at Home. Dissertation at Sainsbury’s. MSc Geographic Data Science, University of Liverpool, PhD Geographic Data Science. Slides
  • Christian Tonge, Movement Strategies. MSc Geographic Data Science, University of Liverpool, and Cristobal Montt, Movement Strategies. MSc Data Science, City, University of London. Dissertations at Movement Strategies. Slides

1400-1505: Alumni presentations (continued) and panel discussion. Session recording (Ushakova 1:48, Samson 21:29, Panel 37:26)

  • Alumni presentation: Dr Anastasia Ushakova, Senior Research Associate, University of Lancaster. Dissertation at British Gas.
    MSc Public Policy, UCL; PhD Computational Social Science. Slides
  • Alumni presentation: Nick Samson, Associate Director, CBRE. Dissertation at British Gas. MSc Geographic Information Science, UCL. Slides
  • Panel Discussion. The next 7 years. Achievements and ambitions: Alex Singleton, Deputy Director (Liverpool), CDRC;
    Samantha Hughes, Analytics Innovation Manager, Avon; Martin Squires, Director of Advanced Analytics, Pets at Home.
  • Thanks & conclusion: Professor Paul Longley, Director, CDRC

Nick Samson, 2014 MDS alumnus. Dissertation at British Gas. Project title: Can smart meters save consumers and British Gas money and carbon by pinpointing which consumers are most likely and best placed to install insulation in their homes?