Details of Grant 

EPSRC Reference:	GR/S79503/01
Title:	New statistical tools for customer value management
Principal Investigator:	Hand, Professor D
Other Investigators:	Crowder, Professor M
Researcher Co-Investigators:
Project Partners:
Department:	Mathematics
Organisation:	Imperial College London
Scheme:	Standard Research (Pre-FEC)
Starts:	11 February 2004	Ends:	10 February 2005	Value (£):	5,065
EPSRC Research Topic Classifications:	Mathematical Aspects of OR Statistics & Appl. Probability
EPSRC Industrial Sector Classifications:	Financial Services
Related Grants:
Panel History:
Summary on Grant Application Form
This application is for travel funds to support Prof Wojtek Krzanowski in approximately twice- weekly visits from Exeter University to Imperial College London, during his sabbatical year (2003-4) to collaborate on two joint projects with Prof David Hand and Prof Martin Crowder.Project 1: Implicit classification:This project aims to develop statistical models which will allow one to predict the likely future behaviour of people (or, indeed, other objects) so that some action can be taken. To permit an appropriate action to be taken, people are partitioned into a set of behaviour classes. Since we are concerned with future behaviour, at the time at which the prediction is made, the behaviour variables will not have been observed. Instead, a set of predictor variables (e.g. application form details) will have been observed and these must be used to assign people to behaviour classes. The problem thus has two parts: partitioning the behaviour space in an appropriate way and constructing a predictive model. Traditional approaches all treat these two parts separately, which is demonstrably suboptimal. We have developed a new type of model which combines the two parts, and we wish to develop and extend that model to make it applicable in a wide variety of situations.Project 2: Customer value review/intervention processExisting models of customer value are relatively simplistic, and often fail to take account of random aspects of the processes customers experience, such as the stochastic nature of the customer over time. We intend to develop models which allow for this, and also to incorporate random customer effects, to reflect the fact that even superficially similar customers are likely to behave differently. Subsequently, we hope to extend these ideas to model and guide the choice of appropriate interventions.
Key Findings
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Potential use in non-academic contexts
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Impacts
Description This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk Summary Date Materialised
Sectors submitted by the Researcher
This information can now be found on Gateway to Research (GtR) http://gtr.rcuk.ac.uk
Project URL:
Further Information:
Organisation Website:	http://www.imperial.ac.uk