The CDRC offers a range of training courses aimed at enhancing capacity in data analytics and data visualisation methods.  We have a number of courses coming up over the next few months in Leeds and London. If you’re looking to grow your skills set in these areas, consider booking now as places are filling fast.

Tableau Workshop

Two papers on food waste by Professor William Young, Co-Investigator of the Consumer Data Research Centre, were among the most downloaded from Resources, Conservation and Recycling Journal at the end of 2017, suggesting a renewed interest in issues surrounding sustainability and responsible consumption among food industry customers.

The result of a collaboration with supermarket giant Asda exploring its customers’ food shopping habits, the research has led to several useful applications by Asda, for example:

• The Love Food, Hate Waste Campaign, which focuses on providing practical tips on how to store food to avoid waste and creative recipes for using up surplus or leftover food.
• A more nuanced approach to labelling for ‘use by’ and ‘best before’ dates by the retailer, for example in removing some best before labels altogether to avoid confusion over when food is and isn’t safe to eat and reducing prices on the day of use by.
• Responding to the research finding that 85% of Asda customers want help in reducing food waste, the retailer worked with local communities to create Community Life Champions.

The most notable success of the application of the research was the finding that customers who applied the in house recommendations saved an average of £57 a year by reducing their food waste. The research and its applications were  discussed at a parliamentary reception, in June 2016, hosted by MP Hilary Benn. For more on this, see here.

The first paper is ‘Bringing habits and emotions into food waste behaviour’. This research project set out, in partnership with Asda, to explore the relationship between habits and emotional determinants and food waste behaviours. Using a combination of the theory of planned behaviour (TPB), the theory of interpersonal behaviour, and the comprehensive model of environmental behaviour, the research project created a set of questionnaires sent to 172 Asda customers over 14 months. Collating the answers found, unusually, that participants who experienced more negative emotion when thinking about food waste actually intended to reduce their waste but instead ended up wasting more food. The project highlighted the importance of taking emotions and intentionality into account when it comes to consumer food waste behaviours.

In the second paper, ‘Can social media be a tool for reducing consumers’ food waste? A behaviour change experiment by a UK retailer’, the premise that social media can be a key influencer of people’s behaviours was interrogated by collaborating with Asda to mount a campaign which encouraged reduction in food waste among Asda customers across Facebook, e-newsletter and its print magazine. The results indicated that use of social media in positive messaging campaigns was no more compelling than use of other media and thus called into question other studies which have privileged social media as a key influencing tool.

Professor William Young, who is Co-Director of the Sustainability Research Institute at the University of Leeds, contributed to both papers. Professor Young’s research focuses on developing theoretical frameworks and applied tools that understand and change consumer behaviour with a view to increasing sustainability and reducing environmental impacts caused by consumption.

On working with Asda he said: “Working with a large scale retailer like Asda, and its millions of customers, has been an invaluable experience. Not only have we come away with real, measurable insight from shoppers but we’ve also seen the direct correlation between our recommended actions and tangible behavioural change.”

The CDRC are collaborating with GISRUK 2018 to host a data challenge that has a particular focus on Brexit. Entrants are encouraged to get their submissions in to be in with a chance of winning a £500 prize.

Challenge
We invite researchers intending to register as GISRUK 2018 conference delegates to develop  a novel analysis or visualisation of CDRC and associated data in order to investigate the hypothesis set out in the Economist article “The immigration paradox Explaining the Brexit vote” (Jul 14^th 2016)[1] that argues that the rate of change in number of migrants in an area rather than the total headcount influenced the Brexit vote. We welcome analysis based on parts or all of the CDRC data listed below as well as analysis that links this with other CDRC data and other data holdings.

Issues that might be addressed include but are by no means limited to:

• Whether Local Authority district is the most appropriate scale at which to ground analysis
• Whether country of birth or ethnicity as defined by CDRC is the best predictor of voting behaviour
• Whether the country of birth of recent immigrants plays any role in shaping voting intentions
• Whether enfranchised members of recently arrived ethnic minority groups are themselves likely to vote for Brexit
• Whether established party political affiliations affect the share of the Brexit vote
• Whether voting behaviour varies according to other local, Regional or national circumstances.
  
  Data
  CDRC available to download at https://data.cdrc.ac.uk/dataset/gisruk-data-challenge-2018
• EU Referendum Result Data
• CDRC small area predicted ethnicity/citizenship data from 1998-2017. The data in the zip file contained here is for use for the GISRUK Data Challenge 2018 only. The data must not be republished in its unaggregated form.License: The data is copyright and database right Consumer Data Research Centre 2018. All rights reserved. Contains data derived from datasets from various sources, some of which are Crown Copyright National Statistics.
  
  Conditions
  A requirement of one of the data source providers is that access to this data is restricted to participants in the CDRC GISRUK Data Challenge. Participants do not need to be GISRUK delegates at the time of getting their submissions in, but, in the event of becoming one of the four finalists, must be willing to register, attend and present at GISRUK which will be held at the University of Leicester, 17 – 20 April 2018. In order to the access the data please email the administrator for the Challenge, Oliver O’Brien, at o.obrien@ucl.ac.uk, confirming that you accept the conditions below. You will then be emailed the password needed to unlock the files.
  
  License
  The data is copyright and database right Consumer Data Research Centre 2018. All rights reserved. Contains data derived from datasets from various sources, some of which are Crown Copyright National Statistics.
  
  Submission
  Applicants should inform CDRC of their intention to participate in the Challenge to o.obrien@ucl.ac.uk by the 11^th February 2018, to include:
• title of paper
• author(s)
• institution  Applicants should prepare a two A4 page case study of their analysis and submit to o.obrien@ucl.ac.uk by the 4^th March 2018. These summaries will be used to select 4 finalists projects to be presented at the GISRUK conference. Finalists will be notified by the 19^thMarch.The best analysis based on the case study and presentation as judged by a panel made up of CDRC staff and GISRUK organisers will be awarded a £500 prize. The four finalist case studies will be made available on the CDRC website and any outputs made available through the CDRC open service.
• Research submitted to CDRC for the challenge can then be subsequently published by applicants themselves, if desired, regardless of whether it is chosen for presentation at GISRUK 2018. Applicants may not however carry out or publish further/alternative substantive research with the data beyond what they have submitted to us, due to the above restrictions stipulated by an upstream data provider.
• The four finalist case studies will be made available on the CDRC website and any outputs made available through the CDRC open service
  
  Enquiries 
  For all enquiries please contact Challenge Administrator Oliver O’Brien, o.obrien@ucl.ac.uk.

[1] https://www.economist.com/news/britain/21702228-areas-lots-migrants-voted-mainly-remain-or-did-they-explaining-brexit-vote

Staff and students from the Consumer Data Research Centre, based in the UCL Geography department have won this year’s departments annual xmas quiz!

Three circles, following a late arrival into the quiz hall, quickly settled using the only remaining table, to join about 30 other quiz teams, in what were very challenging rounds of questions.  Although we struggled most on the Name the Place picture round (the answer being Micronesia), we made up points in the Name the TV Theme Tune, Sports and Patterns rounds, owing successes to specific team members contributing their knowledge in these subject areas!  We thought the patterns round was the most intriguing as it involved naming the city by its night lights and naming the city by the cycle route.

The prize consists of a bottle of Rioja, Big tube of Haribo sweets, a box of Celebrations chocolates and a box of Cadburys heroes!

Congratulations to the team!  People in photo from left to right:  Karlo Lugomer, Jaini Shah, Oliver O’Brien, Ffion Carney, Guy Lansley & Aly Lloyd

Dr Chris Till, co-investigator on one of the projects funded by the CDRC Innovation Fund, provides his views on using big commercial datasets critically.

This month I started working on a new project with colleagues from Leeds Beckett University and The University of Leeds which will use self-tracked data to assess demographic differences in activity patterns.

This research is funded by the Economic and Social Research Council (ESRC) and the Consumer Research Data Centre (CDRC). We will be using data held by the CDRC which has been gathered by an app called Bounts. This app connects to other fitness tracking tracking apps and rewards activity with points which can be exchanged for prizes and discounts. The data generated by the app (which includes the types of activity engaged in, distance, steps, the source of the data as well as basic demographic data on the users) will be combined with consumer profiling datasets and categories (also made available through the CDRC).

Access to these data should help us to get an understanding of who is using activity tracking apps (in relation to gender, income, location and other proxies for social class), in what ways they are using them and whether they are related to higher levels of activity.

This should also help us to investigate if the economic and social environment in which an individual lives is associated with activity (or inactivity) levels and identify if technology use is socially patterned and if it either reduces or increases existing social inequalities.

A second strand of the project will assess the effectiveness of a community national weight management intervention through using similar data matching with consumer datasets. This should also help to investigate if  engagement with weight management interventions is socially patterned.

I think the efficacy of self-tracking approaches to behaviour change is largely taken for granted with many individuals choosing to use step-tracking apps and fitness bands (such as Fitbit). They are also increasingly being pushed through public health campaigns such as such as the NHS “Couch to 5k” app and Sheffield City Council’s “Move More” (which uses an app to facilitate competitions between workplaces and schools).  Workplaces are also increasingly using self-tracking systems to encourage more activity and better engagement at work through competitions and challenges.

While there is some evidence to suggest that these kinds of apps and devices might be effective at behaviour change it is not clear to what extent their use (and effectiveness) are socially patterned. So, for instance, if these interventions are not effective for those who are most in need of them perhaps they need to be re-designed or other approaches entirely are needed.

I am also excited about this project on a methodological level as we will be using commercial datasets and categorisations of populations. Sociologists (including me) have been critical of the collection of these kinds of data and the categorisations which they have enabled. Consequently they are often quite squeamish about using these kinds of data themselves. This is exacerbated by a broader antipathy towards quantitative methods amongst sociologists (at least in UK) who often see it as incompatible with a “critical” approach to analysis. Mark Carrigan has written very well on this recently.

My thinking around this has been influenced by David Beer’s work on the use of “digital by-product” data and “commercial data” and his position that use of these data can enable critical social science. Perhaps sociologists even have a responsibility not to leave the analysis of these kinds of data to commercial enterprises. Big data can be used for control or to sell products but might also be able to highlight social inequalities and to challenge or improve social policy interventions.

Chris is part of the research team working on the Data driven, social, economic and spatial profiles; obesity and physical activity project which is funded by the CDRC Innovation Fund.  The views in the above article, which was originally published on THIS IS NOT A SOCIOLOGY BLOG belong to Chris and do not necessarily represent the views of the project team as a whole.

Following the successful launch of the CDRC indicator ‘Access to Healthy Assets and Hazards’ (AHAH), the overall index of how healthy neighbourhoods are has been incorporated into Public Health England’s ‘FingerTips’ Wider Determinants of Health Data Resource. The data resource compiles various indicators by Public Health England that are supplied to Local Governments to aid with Public Health decision making, and the inclusion of AHAH represents the importance of CDRC project in measuring health-related features of environments. The FingerTips website also includes wider information of health-related features of cities and regions, and health patterns

https://fingertips.phe.org.uk/profile/wider-determinants/data#page/0/gid/1938133043/pat/6/par/E12000002/ati/102/are/

The research analysis from one of this year’s Masters Research Dissertation student was presented to professionals at an event hosted by the leading residential real estate agent Cluttons.

The event, ‘Unlocking London’s Migration Patterns’, brought together professionals from the public and private sector to delve into the factors impacting upon London’s migration patterns.  Research conducted by Neelam Kundi, from University College London (UCL), titled “Exploring submarket trends in London: a constrained spatial interaction modelling analysis” will be used further by Cluttons to explore the extent to which factors such as affordability, accessibility and house price growth affect a household’s relocation decision.

Kundi’s Spatial Interaction Model will form the foundation of the analysis, which makes use of data from the Census Data for London, 2011, and the Office for National Statistics (ONS).

For more on Neelam Kundi’s research click here.

To read more about the study Cluttons are undertaking click here.

On 20th October 2017 the CDRC sponsored and supported the 14th annual Data Analysts User Group Conference (DUG), hosted at the Royal Society.
The conference focussed upon Data Sharing: New Challenges, Opportunities and Examples…

There were some great presentations and stimulating audience discussion over the course of the day around the conference’s key questions:
1. What important questions am I currently unable to answer satisfactorily?
2. Where might data reside, that could help address these challenges and what should I put in place to make progress?

Presentations

The presentations are now available to watch online:

Chair’s Introduction
Tim Drye, Director of Analysts User Group

“The Generation Deficit and other challenges that are revealed by data analysis…”
Lord David Willetts, Resolution Foundation

CDRC Master Dissertation Awards Presentation
Guy Lansley, CDRC, UCL

“Training needs and the Industrial Strategy”
Jonathan Reynolds, CDRC, Oxford

“New Research Indices: The opportunities from extended data integration”
Paul Longley, Professor of Geography, UCL and Alex Singleton, CDRC Liverpool

“Innovation at the ONS: Novel exploration of new challenges”
Tom Smith, Head of Data Science Campus, Office for National Statistics

“Opportunities from the new Digital Economy Act”
Paul Jackson, Administrative Data Research Network and Darren Tucker & Kate Davies Office for National Statistics

“Identifying Problem Families and their interactions”
Paul Holme, Manchester Combined Authority

“Barclays Local Insights: An example of delivering data to share”
Chris Fuggle, Barclays

“From Cosmology to Customers: the improbable applications of astrostatistics”
Dr Roberto Trotta, Dept of Physics, Imperial College London

Chair’s Final Reflections and the DUG Award

The winners of the CDRC’s 2017 Masters Research Dissertation Programme were recently announced at the Data Analysts User Group Conference.

The CDRC led programme provides the opportunity for students to work directly with an industrial partner and links students’ research to important retail and ‘open data’ sources.  Once again the standard of the projects was extremely high this year, with students working with a range of partners, including Sainsbury’s, Shop Direct, Local Data Company and E.ON.

Prize winner: Yifan Cao and Sainsbury’s

Estimate impact of slot availability on customer demand by using choice-based demand models

The judges liked the way that Yifan Cao spanned the scale from the strategic impact down to the detailed model selection. This project provided a very solid analysis with clear objectives analysis, and results. The output has clear implications for the data provider with the potential to introduce new efficiencies into their service delivery. Further, it was encouraging to see the use of open-source reproducible code and a focus on validation.

View Project Abstract

Runner up: Christian Tonge and Movement Strategies

An exploration of mobile data: towards proximity based passenger sensing on public transport

The judges felt that the two runner projects were great examples of dissertation programme from a commercial perspective. Both Christian Tonge and Jon Haycox explored new techniques and data sources that will have future consequences.

Christian Tonge’s project which examined the opportunities presented by New Forms of Data for understanding human mobility patterns. Such analysis is increasingly important as we seek to exploit the potential of New Forms of Data.

View Project Abstract

Runner up: Jon Haycox and E.ON

Electric vehicle charge point placement optimisation

The judges said that Jon Haycox’s project was forward-thinking, on a topic which is going to increasingly interest academics and practitioners alike. The thesis was well constructed and incorporated a broad range of techniques and data. Again, great to see use of open-source tools project where charging points represent a significant potential change in behaviour, so it requires imagination to be able to use existing data constructively.

View Project Asbstract

Other projects completed this year included:

• An exploratory analysis of the temporal fluctuations in footfall around Hammersmith town centre in relation to Business Improvement District events
• Customer pathway and in-store activity – Sainsbury’s
• Customer value modelling – how sensitive is the model to change? – Shop Direct
• How competitive is propensity score matching using ‘address embeddings’ with supervised classification for record linkage tasks? – LDC
• An evaluation of the relationships between construction developments and retail vacancy – LDI and Barbour ABI
• Pricing optimisation – a key tool in successful retailing – Shop Direct
• Exploring submarket trends in London: a constrained spatial interaction modelling analysis – Cluttons
• Where next for Parsons Bakery? A preliminary quantitative location assessment exploring the link between demographics, competition and other variables. – Parsons Bakery
• Propensity modelling – moving beyond standard regression models & explorations into online engagement – Shop Direct
• Identifying Socio-Spatial Inequalities in Student Housing in London – Knight Frank
• The impact of the night tube on Westminster’s Night Economy – City of Westminster
• Can harnessing the demographic characteristics of store catchments improve the planning of promotions and pricing strategies? – Marks & Spencer
• An application of statistical and spatial analysis techniques to engineer callout data from a UK telecommunications company

View all previous projects

2018 Retail Masters Dissertation Programme

We are now seeking proposals from businesses for new projects due to commence next spring (2018). Further Information

We hope to advertise the 2018 opportunities towards the end of the year.

Should you have any queries relating to the programme, please contact Guy Lansley.