Available Projects

Strategic role of data analytics in commercial marketing 

Lead supervisor: Todd Hartman, University of Sheffield
Start Date: October 2017

Commercial organisations now have unprecedented amounts of data on consumer behaviour, market dynamics, buying patterns, and consumer characteristics. The challenge is how to draw meaningful information and insights from this data to inform strategic decisions about product development and marketing. This project offers an outstanding opportunity to work with Linney, a world-class, multi-channel marketing services […]

Does cognitive dissonance predict cross-domain belief consistency and online sharing of vegetarian dietary choices?

Lead supervisor: Nick Shryane, Social Statistics, University of Manchester
Start Date: October 2017

Part one of this study will be an investigation into the consistency of attitudes and beliefs relating to morally charged issues such as animal welfare, gender stereotypes and social equality, comparing vegetarians and non-vegetarians. Cognitive dissonance theory (Festinger, 1957; Ong, Frewer, & Chan, 2017) predicts greater consistency for closely-related attitudes and behaviours (e.g. vegetarians concerned […]

Housing market search: the economic, social, and behavioural aspects of moving home and its implications for understanding household trajectories

Lead supervisor: Stephen Hincks, University of Manchester
Start Date: October 2017

For the individual, the decision to move home is a significant one, laced with anticipation, stress and excitement. The decision to move is one of a number of decisions that will be made during the life cycle of the household that will each shape the pathway the household follows. Although search has been recognised as […]

Automating polling predictions using text mining

Lead supervisor: Sophia Ananiadou, University of Manchester
Start Date: October 2017

Traditional polling techniques based on telephone and online polls used by YouGov and other pollsters were not able to predict the correct outcome in the recent EU referendum and similarly there has been a gap for some recent elections between prediction and results. Well known issues with traditional polling methods include demographic bias, small sampling […]

Semantic Mining Data of Survey Data: making sense of rich data sets

Lead supervisor: Uli Sattler, University of Manchester
Start Date: October 2017

Data gathered from multiple linked surveys has great potential that we plan to unlock in this project. We have developed a framework that mines incomplete data while taking rich background knowledge – in form of OWL ontologies – into account, and that has been shown to be capable of generating rich hypotheses that reflect interesting […]

Multi-sensor Data Fusion for Smart Cities

Lead supervisor: Lyudmila Mihaylova, University of Sheffield
Start Date: October 2017

The integration of real time information from the interned of things and multiple sensors offers the potential to transform how cities are run, to improve the quality of life and to make cities more efficient and sustainable. This PhD project will draw on the relevant academic literature and deploy cutting-edge analytical methods to explore how […]

Data analytical approach to crime prevention and resource allocation

Lead supervisor: Gwilym Pryce, University of Sheffield
Start Date: October 2017

This project will explore ways to exploit data resources held by South Yorkshire Police and other agencies and departments to help inform strategic decisions and specific interventions. Drawing on data analytical methods and relevant social theory, the project will explore how linking data from crime, social services and education could help identify vulnerable individuals who […]

Economic and social impacts of HS2 

Lead supervisor: Lyudmila Mihaylova, University of Sheffield
Start Date: October 2017

High Speed 2 (HS2) is Britain’s planned second high speed rail network (after HS1 which connects London with the Channel Tunnel). It represents one of the UK’s largest infrastructure projects and has the potential to transform transport connections between England’s major cities. Nevertheless, HS2 remains controversial and is fraught with uncertainties. Drawing on the relevant […]

Evaluation of consumer transactions as a source of dietary consumption information

Lead supervisor: Michelle Morris, University of Leeds
Start Date: October 2017

This project will compare a method of self-reported dietary assessment, which is often subject to reporting bias, with an arguably objective measure of food purchasing records from consumer transactions on store loyalty cards. There will be a strong methodological focus to the project using the two data sources to better understand patterns in dietary behaviours […]

Automating detailed urban data extraction from high resolution aerial imagery

Lead supervisor: Dani Arribas-Bel, University of Liverpool
Start Date: October 2017

Ordnance Survey are partners in the CityVerve project in Manchester. This project is building a city Internet of Things demonstrator, led by Manchester City Council and Cisco. OS is supplying geospatial data to CityVerve. We are interested in examining the framework of data needed for the detailed monitoring of the city environment allowed by an IoT […]

Predictive data analytics for urban dynamics

Lead supervisor: Nick Malleson, University of Leeds
Start Date: October 2017

Identifying the factors that encourage and discourage attendance in urban spaces is vital from both academic and practitioner perspectives. For policy makers, an understanding of what attracts people to city centres, and what discourages them, is vital for urban planning and emergency management. From an academic perspective, understanding the drivers of footfall is essential in […]

Scalable analytical framework for spatio-temporal data analysis

Lead supervisor: Francisco Rowe, University of Liverpool
Start Date: October 2017

There are many applications for spatio-temporal data analysis for solving real-world problems. In the context of a Big Data system, spatio-temporal data are often utilized along with other types of data. In Big Data world, generally there are two computational analytical tasks in processing and analyzing spatio-temporal data (data preparation and cleaning is not considered […]

Non linear mixed effect pricing elasticity modelling incorporating different layers of fixed and random effects

Lead supervisor: Alex Lord, University of Liverpool
Start Date: October 2017

Within online retail environments, pricing of products can be more dynamic than might be the case within traditional retail stores. Furthermore, there are opportunities to explore pricing elasticity through big data; both in new modelling techniques that examine sensitivity of demand in terms of purchase, but also how these shape customer purchasing browsing dynamics. Reference […]

Developing an algorithm for non intrusive cross device customer journey mapping for non self identified customers

Lead supervisor: Danushka Bollegala, University of Liverpool
Start Date: October 2017

  This project will explore new mechanisms for mapping consumer journeys between devices in a way that are not invasive to the consumer and are constrained by ethical and legislative frameworks. This will involve analytics associated with both browsing histories over multiple platforms and their fusion alongside probabilistic linkage to transaction outcomes. Reference number LV10 […]

Modelling the impact of the physical location of the customer on online browsing and purchase behaviour

Lead supervisor: Les Dolega, University of Liverpool
Start Date: October 2017

The intersection between online and offline consumption are of critical interest to retailers; both in terms of overall market share but also in terms of channel switching or omni-channel retail. For online only retail there is little evidence about how the geography of physical retail provision has impact upon online shopping rates. This study will […]

Modelling the impact of predicted and actual weather on online customer behaviour

Lead supervisor: Andy Morse, University of Liverpool
Start Date: October 2017

Within the context of physical retail stores, there is some evidence to suggest that for certain product categories there is a relationship between purchasing behaviour and weather conditions. However, there has been much more limited study about how this relates to online consumption. This project will look at exploring patterns of online spend between categories […]

A topological data analysis of big spatio-temporal urban data

Lead supervisor: Dani Arribas-Bel, University of Liverpool
Start Date: October 2017

One challenge of working with big spatio-temporal data relates to the  extraction of information about the underlying structure from what can be dynamic and often highly dimensional data. Topological Data Analysis has been used within a range of applications to extract structure from data; in particular focusing on underlying structure from within large and complex […]

Understanding dynamic pedestrian movements and transport flows within urban environments through sensor data

Lead supervisor: Alex Singleton, University of Liverpool
Start Date: Octber 2017

Sensor technology within cities are enabling new methods of estimating both transport and pedestrian flows. However, there are a range of technical challenges associated with the practical use of the data generated, and in particular how different sources can be conflated. This project will explore various mechanisms of data fusion and will build models of […]

Predictive geodemographics

Lead supervisor: Prof. Alexis Comber, University of Leeds
Start Date: October 2017

One of the many criticisms of geodemographic classifications is that they are static – typically built using census data. They are out of date as soon as they are released, representing on a snap shot of what the population was like 3 years previously, this being, on average, the time taken for census agencies to […]

Product bifurcation and omni-channel retail

Lead supervisor: Les Dolega, University of Liverpool
Start Date: October 2017

As a retailer with both an online and in store presence, this project will consider how product consumption varies between channels (including omni channel); and importantly  how these trends have and are evolving over both space and time. This project implement time series methods that develop models which estimate these future trends, and have considerable […]

Weather and the impact on high street retail

Lead supervisor: Les Dolega, University of Liverpool
Start Date: October 2017

This project will explore the integration of weather condition data at a local level with retail outcomes in terms of overall purchase and product category stratification. This will have a particular focus on temporal trends, and how forecast data might be incorporated into models associated with spend, offers or product purchase propensity and pricing. Reference […]

Using YouGov structured panel data to predict tweet content

Lead supervisor: Mark Elliot, University of Manchester
Start Date: October 2017

The project would aim to use the linked Twitter accounts within the YouGov panel to build prediction models of tweet content. Understanding why people tweet certain content is a complex issue. Key research questions are: Are tweets predicted attitudinal data, demographics, education and so on? Do changes in any of this structured data produce changes […]

Dealing with missing data in online ‘opt-in’ non-probability panels

Lead supervisor: Natalie Shlomo, University of Manchester
Start Date: October 2017

Online ‘opt-in’ non-probability panels are increasingly being used by polling and marketing agencies due to their low costs and timeliness.  Unlike traditional probability surveys they sample from a dataset of ‘opt-in’ panel members (which can be larger than a million for some companies) in a relatively high frequency fashion (e.g., daily). Despite their popularity they […]

Evaluating the merits of survey and observational data in National Election Studies

Lead supervisor: Jane Green, University of Manchester
Start Date:

This project would build on the existing 2015 internet module of the British Election Study (iBES) collected by YouGov that merges survey and observational social media data. The primary goal would be methodological in nature, and focus on evaluating the validity and robustness of each data source as a measure of political attitudes and behaviour. […]