Prof Andrew Smith
Professor of Consumer Behaviour at Nottingham University Business School, Andrew has extensive expertise in consumer behaviour theory, the analysis of consumption patterns and application of novel time series analysis to consumer purchase data. He has published widely in the fields of: consumer behaviour and psychology; customer loyalty schemes; complexity and consumption; and consumer privacy.
Dr James Goulding
Prior to N-LAB James led the Data Science programme at the RCUK funded Horizon Institute. His core research is in the rapidly growing field of Machine learning with Big Data, focusing on information theoretic techniques to analyse large-scale human behavioural data. He has won an ACM Engelbart prize for work in data theory, a Centre for DE prize for data visualization and also runs the NHS Data Science programme.
Mark specializes in Geospatial methods, with a specific focus on mapping in emerging economies and markets – considering how data science methods must be adapted for those regions. In addition to his fellowship, he consults for the World Bank on implementing mapping programs across the developing world (with a focus in East Africa) and the development of policy.
Dr Gavin Smith
Data Science Lead
Gavin specializes in temporal data mining and machine learning, focusing on development of novel data driven approaches to predict human behaviour in time series. He also researches how to ensure that techniques are applicable in real world scenarios, producing interpretable results. Past work includes theoretical analysis of the limits of predictability in human movement, optimizing symbolisation techniques in time series and dynamic topic modelling (customer mission analysis) in transactional data.
Innovate UK KTP Fellow
Vanja, a joint KTP researcher with Krow Marketing, developing the concept of a Change Readiness Index, in the context of the consumers’ transactional behaviour. The aim is to assist with retargeting suggestions, sales predictions and to generate directives for creative work. This is supported by a qualitative approach that finds connections between social patterns and predictions extracted from the data via engagement with cultural context.
Dr Duncan Barrack
Duncan’s main work on the project centered on novel forms of event process clustering (predominantly generated from human transactinoal data). He has also worked on the development of machine learning techniques for New Product Introduction. When he has the time, he can found competing on the on-line data science platform Kaggle (where has has achieved master status, recently winning the INRIA sponsored brain computer interface (BCI) challenge).
Affiliated PhD Students
Georgiana’s background is in social marketing and consumer behaviour, and she is develops new methods to combine machine learning with qualitative research to better understand the people behind Big Data (via notions of contextualisation, consilience and ethics).
Will’s research focus is in combining data mining and marketing research. He is pioneering a new data-driven form of Life Event Analysis, that aims to detect important points within a consumer life course (e.g. moving house) through analysis of digital footprint datasets.
Haixia is a computer scientist now researching Idea Mining – automatic generation of ‘ideas’ from Big Data. This occurs via identification of key concepts in a dataset, which can then be reogranized into novel combinations to produce new ‘ideas’.
Gregor’s research examines how mining CDR data can generate Social Good in areas of mobility mapping and urban planning. Combining HCI and machine learning in these are opens up huge policy and market opportunities, particularly in fast changing environments such as East Africa.
Sam is exploring new data science methods to detect those at risk of acquiring debt they are unable to manage Initial models focus on a person’s impulsivity and it’s relation to unmanageable debt, whilst also investigating whether this can be detected in social media usage.
Integrating Psychology and Big Data Research.