Machine learning methods for next generation customer service

Applications are invited for a three-year PhD studentship. The studentship will start on 1 October 2021.

To apply please use the online application form. Simply search for PhD Mathematics and Statistic, then clearly state that you are applying for a PhD studentship within the School of Engineering Computing and Mathematics and name the project at the top of your personal statement.

Online application

Take a look at the Doctoral College's general information on applying for a research degree.

Project description 

The COVID pandemic has shown the importance of the smooth running of the UK’s broadband infrastructure, in order to, for example work from home. For telco companies such as British Telecom (BT), it is important to dynamically detect customer requirements and hence predict the best actions to provide excellent customer service. This allows the customer to fully use the broadband services they pay for, and the company to keep a satisfied customer.

Although parts of the solution are available, there is no firm understanding of how this can and should be approached in a strategic fashion. This project will develop cutting edge statistical/machine learning techniques and orchestration of disparate big data sources to build this capability. The designed solutions will bring the benefit of saving valuable resources as well as improving customer experience and quality of services that businesses provide. The project will be done in cooperation with analysts from BT Research and using extensive data bases owned by BT. Statistical models and machine learning methods that perform supervised classification will be developed and tested. In particular, the approaches that will be explored are: (a) ensemble methods such as families of classification trees; (b) artificial neural networks; (c) Bayesian networks for modelling customer churn. The methods will be designed to cope with high dimensional data of large size. Thus, the aspect of decreasing the level of complexity of the models and/or data will be addressed through appropriate variable selection and/or dimension reduction techniques.

Eligibility 

Applicants should have (at least) a first or upper second class honours degree in an appropriate subject and preferably a relevant MSc or MRes qualification. 

The studentship is supported for three years and includes full home tuition fees plus a stipend of £15,609 per annum (2021/22 rate). The studentship will only fully fund those applicants who are eligible for home fees with relevant qualifications. Applicants normally required to cover international fees will have to cover the difference between the home and the international tuition fee rates (approximately £12,697 per annum).

If you wish to discuss this project further informally, please contact malgorzata.wojtys@plymouth.ac.uk. However, applications must be made in accordance with the details shown below.

General information about applying for a research degree at the University of Plymouth and to apply for this position please visit: https://www.plymouth.ac.uk/student-life/your-studies/research-degrees

Please mark it FAO Doctoral College and clearly state that you are applying for a PhD studentship within the School of Engineering, Computing and Mathematics.

For more information on the admissions process email the Doctoral College, doctoralcollege@plymouth.ac.uk.

The closing date for applications is 19 April 2021. Shortlisted candidates will be invited for interview the week beginning 3 May 2021. We regret that we may not be able to respond to all applications. Applicants who have not received an offer of a place by 31 May should consider their application has been unsuccessful on this occasion.