Home » Archives for April 2020

Month: April 2020

CDRC to adopt key role in powerful new COVID-19 data alliance

by


CDRC to adopt key role in powerful new COVID-19 data alliance

The Consumer Data Research Centre will work through its parent organisation Leeds Institute for Data Analytics to provide a new COVID-19 data alliance with scientific expertise and access to global academic research networks.

Leeds Institute for Data Analytics (LIDA) has worked alongside consortium-leader Rolls-Royce to develop the concept and will take a founding position in a new alliance of data analytics experts challenged with finding new, faster ways of supporting the response to COVID-19 and subsequent global recovery.

Early alliance members are Leeds Institute for Data Analytics, IBM, Google Cloud, The Data City, Truata, Rolls-Royce and ODI Leeds. The alliance will be facilitated and co-ordinated by innovation specialists, Whitespace.

Together the initial wave of members brings all the key elements of open innovation; data publication, licensing, privacy, security; data analytics capability; and collaborative infrastructure, to kick off its early work and grow its membership.

Emergent will combine traditional economic, business, travel and retail data sets with behaviour and sentiment data, to provide new insights into – and practical applications to support – the global recovery from COVID-19. This work will be done with a sharp focus on privacy and security, using industry best practices for data sharing and robust governance.

As part of LIDA’s involvement in Emergent, researchers will have the opportunity to access these data sets using collaborative platforms which have been established by CDRC.  The academic community will be encouraged to articulate and engage in projects to help understand the changes we are seeing in human activity and social behaviour as a result of COVID-19.

Emergent models will help get people and businesses back to work as soon as possible by identifying lead indicators of economic recovery cycles. Businesses small and large around the world, as well as governments, can use these insights to build the confidence they need to take early decisions, such as investments or policies, that could shorten or limit the recessionary impacts from the pandemic.

The alliance is voluntary and insights will be published for free.

Professor Mark Birkin, who leads both the Consumer Data Research Centre and Leeds Institute for Data Analytics commented:

“Increasing numbers of academics and other commentators are now recognising the potential for commercial organisations to share important data to help in the battle against COVID-19.

An established investment in data sharing capability and analytics capacity makes LIDA ideally placed to lead such conversations.

We are delighted to bring our skills and expertise as a founder member in the Emergent consortium, which offers such enormous potential to deliver benefits to society – and which are so badly needed at this difficult time.”

Connecting business and the academic community

The Consumer Data Research Centre was created in 2014 from a substantial award in the ESRC Big Data Network.  Leeds Institute for Data Analytics at the University of Leeds was then established from the union of the CDRC (Leeds) with the MRC Centre for Medical Bioinformatics.

Since then, both LIDA and the CDRC have been actively promoting the mutual benefit of collaborative projects between corporate partners and the academic community, with researchers working in cross industry teams to undertake scientific research that produces real world insights.

The COVID crisis has further highlighted the importance of these types of collaboration, with governments and their advisers seeking real world insights into mobility, behaviour and human contact networks.

LIDA will be utilising its extensive network – which includes the ESRC Business and Local Government Data Centres, the Alan Turing Institute, Doctoral Training Centres in Data Analytics and Society (ESRC) and Artificial Intelligence (UKRI) – to connect partners with academic experts from multiple institutions and disciplines.

Providing a secure infrastructure

LIDA and IBM will be providing the infrastructure to enable alliance partners to share and compute their data.

Where there is a need to use secure data, partners will be granted access to LIDA’s ISO accredited infrastructure, which will enable them to perform analysis in a safe and controlled environment. Partners using the LIDA infrastructure will be supported by project management and technical support teams from the Consumer Data Research Centre.

For projects using public data, partners will use IBM’s environment and any non-sensitive data will be shared via emergentalliance.org.

Join Emergent

Caroline Gorski, Global Director, R2 Data Labs, the Rolls-Royce data innovation catalyst which started the alliance, said: “We want the global economy to get better as soon as possible so people can get back to work. Our data innovation community can help do this and is at its best when it comes together for the common good.

“People, businesses and governments around the world have changed the way they spend, move, communicate and travel because of COVID-19 and we can use that insight, along with other data, to provide the basis for identifying what new insights and trends may emerge that signify the world’s adjustment to a ‘new normal’ after the pandemic.”

The first challenges have already been issued by the alliance, including one to identify lead indicators of economic recovery which businesses can use to build the confidence they need for investment or activities that will shorten or limit any recessionary impact from the virus.

Emergent hopes to rapidly expand its network of data owners and has set up a website for potential members to register their interest at emergentalliance.org.

CDRC (Leeds) also encourages prospective academic participants to contact us directly at k.r.norman@leeds.ac.uk to receive further updates.

Analysing student eating habits

by


Analysing student eating habits

Scientists have for the first time used anonymous data from pre-payment food cards to get a unique insight into the eating habits of first year university students.

Data scientists from the Consumer Data Research Centre at the University of Leeds have been able to build a detailed picture of what 835 students ate, and when, by analysing the data linked to their pre-payment food cards.

The cards revealed what they were buying in the campus refectory and associated food outlets.

The analysis gives the most accurate picture to date of first year student diets. Many previous studies have used food diaries, but their accuracy can be variable because they rely on the student remembering exactly – and being honest about – what they have eaten.

Dr Michelle Morris, a University Academic Fellow in Health Data Analytics based at Leeds Institute for Data Analytics, said understanding student diet had public health implications.

Previous studies in the UK and the US have shown that “fresher” students are at risk of weight gain, probably as a result of the lifestyle changes that come with starting university.

In the US, they talk of the “Freshmen 15”, the 15lbs (6.8kg) that students put on. In the UK, research indicates the average student gains 7.7lbs (3.5kg).

The findings, Assessing diet in a university student population: A longitudinal food card transaction data approach, have been published in the British Journal of Nutrition.

The study, which pre-dated the coronavirus outbreak and followed the students aged 18 to 24 over their first semester (12 teaching weeks), revealed student eating habits which clustered around seven dietary behaviours:

  • Vegetarian: with popular purchases being salads, breakfast cereals, yoghurt and fromage frais and a notable absence of meat products
  • Omnivores: which included the most average amounts of all products purchased, with above average amounts of ice cream, desserts and cakes, breakfast cereals and fish.
  • Dieters: with above average purchases of soups, pasta, noodles and salad.
  • Dish of the Day: which included above average purchases of meat and meat products.
  • Grab and Go: which included above average purchases of sandwiches, crisps, nuts and eggs.
  • Carb Lovers: with bread, cheese, egg products and pasta being among the top picks.
  • Snackers: with confectionery, crisps, nuts being above average choices.

Dr Morris, said the dietary patterns were ranked on the basis of “healthfulness”, with vegetarian the most healthful and snackers being the least.

She added: “Our analysis shows that although some students followed one dietary pattern throughout the semester many switched between them.

“Some students moved from a more healthy to a less healthy pattern; for example,  some vegetarians switched to an omnivore diet; and vice versa with some of the students who started off as snackers – the least healthful diet – did move to the Dish of the Day which offered a more balanced range of food options.

“Worryingly perhaps, the most popular move was from a dieter pattern, to the snacking pattern.”

Females were found to be heavily represented among the vegetarians (88%) and dieters (80%) while the men dominated the dish of the day (84%) and grab and go (62%) diet patterns.

“This information could be used to target information about healthier eating to students.”
Dr Michelle Morris, Leeds Institute for Data Analytics

Dr Morris said the most popular dietary pattern amongst the slightly older students, those aged between 20 and 24, was the omnivore pattern of eating – that could be due to the fact that they may already have lived away from home and settled into a more varied dietary pattern.

She said: “The information from this analysis reveals the pattern of the students’ eating habits, and how that changes over time. That is information that could be used to target information about healthier eating to students.

“Research has shown that adult eating habits take root early in adulthood. So, time spent at University is a great time to encourage healthy eating behaviours that could remain with them for life.”

The research was funded by the Economic and Social Research Council through a Strategic Network for Obesity grant. Maintaining the anonymity of the students was of utmost importance at all stages of the research.

Notes to editor

For further information or interview requests, please contact University of Leeds Media Relations and Communications Officer David Lewis via d.lewis@leeds.ac.uk

Home Working and Horizon Scanning

by


Home Working and Horizon Scanning

Work has been transformed by the coronavirus crisis with remote working now the norm for millions of workers. But distance from the office is also providing some opportunities to take a wider perspective of the data landscape and to scan business horizons using data sources that we might have overlooked or never investigated in detail.

The CDRC Data Store remains open for business, and our Open and Safeguarded data products are available as normal. Our Secure labs are closed for the duration of the crisis, but we are still accepting Secure data applications for access when things return to normal.

For students, our Masters Dissertation Scheme is still running with a record number of projects for students to complete in the coming months using business and CDRC data. The scheme gives Masters students registered at any UK university a unique opportunity to engage with horizon scanning or other business problems using novel datasets and interesting business perspectives on applied problem-solving. In the past, many participating students have carried out work at the businesses office, but this year students are being offered opportunities to work with businesses through homeworking for the duration of the crisis. The Scheme still brings together the best of academic and business perspectives upon applied problem-solving. Academic supervisors similarly gain the opportunity to collaborate on potentially high impact research with the business community.

So… if you are a Master’s student interested in collaborating with business, but can no longer do this through fieldwork or primary data collection, why not click here to see if any of the CDRC projects interest you? A number of the organisations that we work with are very keen to use part of their homeworking to coach students in the workings of business, especially if you have relevant skills and ways of working to offer!

We also have the CDRC Data Store which has a wide range of data sets available, some of which may be very useful in your dissertation or current research.

Prioritising food establishment inspections

by

Prioritising food establishment inspections

Populations who frequently eat fast food and live within close proximity of unhygienic food establishments may be at higher risk of contracting foodborne illness than those who do not eat takeaways regularly – but which food establishments are most likely to be unhygienic?

Recent research by CDRC PhD student Rachel Oldroyd uses logistic regression to identify ecological determinants of non-compliant food outlets in England and Wales.  Rachel’s recent paper in Health & Place highlighted:

  • A clear gradient of association is observed between increased deprivation and the probability of non-compliance.
  • Food outlets in the most deprived areas are 25% less likely (OR = 0.75) to meet hygiene standards than those in the least deprived areas.
  • Takeaways, sandwich shops (OR = 0.504) and small convenience retailers (OR = 0.905) are less likely to be compliant than restaurants.
  • Food outlets in large conurbation areas are less likely (OR = 0.678) to meet hygiene standards than those located in cities and towns.
  • Outlets in deprived and urban areas, especially takeaways, sandwich shops and convenience stores should be prioritised for inspection.

You can read the full paper here.