Uncategorised

Students on our MSc in Consumer Analytics and Marketing Strategy were delighted to receive an interactive and informative guest lecture delivered by three speakers from Shop Direct. Shop Direct are the second largest pure play digital/e-commerce retailer in the UK and are the company behind the Very.co.uk and Littlewoods.com brands. We were joined by Tony Birch (Business Modelling Manager) and Nicola Dunford (Data Scientist) from their data science and analytics functions, and Louise Utton (Talent Partner) from their HR team. They introduced Shop Direct and their target customer demographic, ‘Miss Very’.

Tony and Nicola gave an excellent overview of the analytics, data science and modelling functions across their business and brands. They gave a clear distinction between day-to-day analytics and reporting versus larger scale innovative data mining and model building. They outlined the use of self-service systems to enable colleagues from across the business to access routine data (e.g. product sales) and gave specific examples of some of their larger model building projects, particularly in relation to assessing their marketing campaigns. They also discussed some of their novel ‘user experience’ and lab testing, all carried out in-house.

Louise introduced students to the working environment at their ‘Skyways House’ Head Office in Liverpool, including their new training and wellbeing venue ‘The Cube’, and discussed the MSc Dissertation Projects that Shop Direct are offering as part of the CRDC Masters Research Dissertation Programme. Students commented incredibly positively on the usefulness of the session and a number of students have been in further contact with the team in relation to MSc projects and future careers.

Guest lectures are an exceptionally important part of our MSc in Consumer Analytics and Marketing Strategy, giving students direct exposure to the application of their skills in a commercial setting. The interactive nature of this lecture enabled students to have a direct dialogue with managers and data scientists at Shop Direct. We very much look forward to welcoming Shop Direct back for further guest lectures in the future and hope that a number of our students will explore further opportunities to work with Shop Direct.

This introductory webinar is for anyone with an interest in computers, cities and data. Participants learn about the explosion of new sources of data and about changes in urban cities that are currently taking place, as well as the main opportunities and challenges this represents. Special attention is paid to the need to re-think how we approach data in this new landscape to be able to reap the benefits without running into (already solved) problems.

Download Presentation

Download presentation slides

We will be running this course again on Thursday 22 February 2018 – find out more and book online.

I recently attended a 1-day course to learn how to use Tableau visualisation software, hosted by the Consumer Data Research Centre (CDRC) in the Leeds Institute for Data Analytics (LIDA).

On its website, Tableau says that it “helps the world’s largest organizations unleash the power of their most valuable assets: their data and their people”. The shorter version of that is, basically, that Tableau is software to visualise and analyse data. And mostly to visualise at that (for serious analysis you’re probably going to use something else like R or Python). But as for using Tableau as a data visualisation tool, I was very impressed!

The course took us through some examples of how to use Tableau for some increasingly difficult problems. These were interesting and a good way to get the handle of using the software, but I spent most of the time using it on some other data that I’m interested in at the moment. In particular, Leeds City Council have released a load of footfall data from a few cameras that they have dotted around Leeds, and I was interested in trying to look at the flows of people around the city.

It was easy to load the camera data in (just by dragging) and to link it to the camera locations that I had stored as a separate file. Tableau works out which columns represent coordinates and then lets you map the data. The screenshot below shows the camera locations, the the colour and size of the dots determined by the total footfall over the whole time period. The map is pretty rubbish at that scale, it is designed for regional or national mapping, but you can link to MapBox which will give you full control over the basemap. I didn’t do this, but imagine that it is a very useful feature (MapBox is great).

I then began to explore the changes in footfall over time, and this is when I was most impressed. Tableau parsed the time data properly (i.e. by not confusing dates and times for something like text), which was nice, but more importantly it made it incredibly easy to either look at trends over time (e.g. footfall per week over the last few years) or to aggregate to specific times (e.g. total counts on Mondays, Tuesdays, etc.). The figure below shows two examples of this. OK, you could do this with lots of other tools, but I was very impressed at how easy it was. There is also a ‘dashboard’ function that lets you combined plots and make images.

To summarise: I was very impressed with Tableau as a data visualisation tool. The one-day course is probably overkill for people who are fairly confident with modelling/visualisation tools already as it was generally pretty easy to use. But it was still nice to have a day messing around with some data. I don’t know what the price of Tableau is – as a lecturer I am lucky enough to have been given a free license – but if it is affordable then I would certainly recommend it as software to quickly do some useful visualisations of data.

Dr Nick Malleson is an Associate Profressor in Geographical Information Science and a member of the Centre for Spatial Analysis and Policy (CSAP) at the University of Leeds. His primary research interest is in developing spatial computer models of social phenomena with a particular focus on crime simulation. 

CDRC PhD Student Rachel Oldroyd is one of the UK Data Service Data Impact Fellows. Rachel is a quantitative human geographer based at the Consumer Data Research Centre (CDRC)at the University of Leeds, and here discusses how novel types of data are used to detect illness caused by contaminated food or drink.

Affecting an estimated 1 million people at a cost of around £1.5 billion per year (Food Standards Agency, 2011), foodborne illness remains an unacceptably high burden on the UK population and economy. As many victims choose to recover at home without visiting their GP, the number of cases is difficult to measure and severely under reported in national data.

But what is foodborne illness? The World Health Organisation defines it as an Infectious Intestinal Disease caused by the ingestion of a harmful parasite, virus or bacteria, known as a pathogen. A pathogen can infiltrate any part of the food supply chain and can be hard to detect, but will result in symptoms ranging from mild nausea to death. With around 500 annual deaths in the UK attributed to food poisoning, the Food Standards Agency (FSA) are continually developing methods to support their key objective to reduce its incidence.

I currently teach Geographic Information Systems in the School of Geography and I’m studying towards a PhD in the Consumer Data Research Centre, both at the University of Leeds. My research is focused around data analytics for food safety. In particular, exploring the landscape of food safety in the UK and investigating the utility of novel types of data. For the first part of my research I plan to extract geo-demographic variables from the 2011 Census, investigating relationships between these variables and food safety measures (restaurant hygiene scores, hospital admissions and mortality). The second part of the research will focus on the use of novel types of data and Natural Language Processing to detect cases of foodborne illness reported through online reviews and social media. It is hoped that these datasets may provide additional information missed by the traditional GP reporting process.

Many US studies have researched the use of novel types of data for disease detection, reporting timeliness and the inclusion of additional information as key advantages compared to traditional GP data. For example, in a restaurant review, customers may comment on the cleanliness of the restaurant, the quality of the service and/or describe the food they ate. These user-generated comments are extremely useful and are not available from traditional data sources. However, extracting reviews within which customers report illnesses can be difficult. It is not as simple as looking for specific keyword matches, as these will often return false results; for example searching for ‘sick’ may return ‘I’ve never known anyone get sick here’. This is where Natural Language Processing plays its part. A model can be trained to identify sequences of words which refer to illness and return relevant reviews; ignoring those which do not indicate illness.

It’s hoped that this research will have a strong policy impact and will be used to inform and improve the current restaurant inspection process in the UK. Throughout the research I plan to liaise with key industry professionals, including those from the FSA and the local authority to keep the research relevant and timely. I’m delighted to be named as one of the UK Data Service Data Impact Fellows and plan to take full advantage of the scholarship by developing impact through presentations at national and international conferences, disseminating the research through suitable publications and holding stakeholder events and public seminars. Watch this space!

Learn more about the UK Data Service’s Data Impact Fellows and their research in this recent video.

Our Deputy Director, Professor Alex Singleton, dedicated a week to running a workshop at Ritsumeikan University, Kyoto, Japan.

Covering the basics of Geographic Data Science (GIS) and Urban Analytics with particular emphasis upon the study of cities through new forms of data, the final day included presentations of independent student projects that focused upon a range of different application areas. Winning projects were awarded with CDRC branded prizes, including a printed 2017 calendar featuring top maps from our mapping portal, maps.cdrc.ac.uk.

Alex’s workshop was received extremely well and proved to be an useful illustration of code based teaching of GIS  to new users of R.

Course Materials.

The CDRC and UK Data Service have enlisted Dr Daniel Arribas-Bel to host a webinar titled ‘Bringing new forms of data to the study of cities’. For more and to book a place.

I recently completed a half-day course at LIDA on Smartphone Application Development for Data Collection purposes, the course was perfectly pitched so that those without a computer science background (most of us) were able to jump straight in. The course was introductory in nature but with enough expertise to give a sense of what you can expect down the line should you be able to develop your own native application. The course itself covered the different types apps from the more technical native apps to some of the more user-friendly app building tools. The technical details such as coding languages and the software packages you’ll need were explained and we were even given brief demonstrations of.

The course was invaluable for giving me the understanding how these applications could be be used in research. The course covered the important aspects of how data could be collected and stored through smartphone applications, and importantly what considerations you need to make given the different functions an app can have. This level of information and detail allowed me to think about how apps could be used in my own research which is looking at how incentives could be used in travel behavior. To this end it has developed a line of thinking in my research methods which might not have been possible without the opportunity to attend this course.

Connor Walsh, PhD Student, University of Leeds

We are currently confirming the details for the next Smartphone Application Development for Data Collection Purposes course.  To register your interest, please contact e.a.pound@leeds.ac.uk

CDRC Data Science Intern, Molly Asher, is currently conducting a pilot study on the effectiveness of the UK Parliament’s e-petitions system with the goal to determine whether e-petitions have led to a rise in trust in parliament, the development of new engagement with parliament and/or policy changes.

The full project will develop a comprehensive analysis of a parliamentary e-petitioning system, which integrates the views of petitioners, the actual processes dealing with petitions, the public debate surrounding the petitions, the views from policy-makers and the outcomes of petitions. The project adopts a mixed-methods and inter-disciplinary approach, incl. Data Science analysis of all petitions (incl. themes, success probability, geographical representation, timing of signatures, nature of the petition & partisanship) and the petition debates on Twitter (incl. themes, sentiment analysis, nature of the debate, e.g. the level of polarization and partisanship, geographical representation, social network analysis of those involved in the debate).

Molly is currently conducting a pilot study on the petition debates on Twitter and potentially linking them in an analysis of the e-petition data.  She presented her findings at a recent LIDA Seminar:

Data

Molly is currently using the following data for the pilot study project:

• Twitter data collected via the Twitter Streaming API
• UK parliament e-petition where JSON data files are available for download with each petition.

On 6 December 2016 the CDRC co-hosted the annual Oxford Retail Futures Conference at the Said Business School (SBS), University of Oxford. The focus of the event was to explore the current uses and challenges of using consumer data in the retail and supply chain environment, and to discuss developments of data analytics for a range of industry and research purposes.

The day consisted of a series of well received presentations and lengthy panel discussions concerning developments in data acquisition and analysis, understanding areas and activities using new forms of data and the implications of big data for the organisational aspects of firms. Interesting discussion surrounded future directions for the CDRC’s SmartStreetSensor project, the prospects of loyalty card data and using big data to inform organisational decision making.

Attendees and speakers included industry experts representing the likes of Walgreens Boots Alliance, the Local Data Company, GI Solutions Group and pgw Ltd. The day was brought to a close by Martin Squires (Global Lead, Customer Intelligence and Data) from Walgreens Boots Alliance, giving an insightful overview of a practitioner’s viewpoint of the uses of their customer loyalty card data and future directions for data analytics.