Self-adaptive Machine Learning Methods For Outcome Prediction In Real-world Complex Datasets

Applications are invited for a self-funded, 3-year full-time or 6-year part-time PhD project, to commence in February or October 2020. The PhD will be based in the School of Computing and will be supervised by Dr Mohamed Bader and Dr Bryan Carpenter.

Overview

This project will focus on the development of novel machine learning methods for outcome prediction in real-world complex application. The data-sets required in our target areas are very large, and we are investigating the application of techniques from High Performance Computing as enablers in applying machine learning techniques to them. The project will be based on recent work will focus on one more of the following predefined applications:

1. Early outcome prediction in healthcare

In this application the focus will be on MIMIC and eICU database which contains more than 3 million ICU stays and billions of medical measurements that is collected from more than 400 hospitals. Over the past few decades, several severity scoring systems and machine learning mortality prediction models have been developed. However, most of the these methods are static not are not capable  of dealing  with size and speed of the current available data, therefore there is huge need for new and novel Big Data in ICU. The student will  join an existing team working on risk and mortality prediction in ICU. The team has access to an existing preprocessed ICU database that is compatible with several data mining and data analytics tools.

2. Consumer behaviour prediction for digital marketing

This part will take place in collaboration with a leading digital marketing which offers a real-time personalisation and automation across email and web that optimises revenue for e-commerce companies. Its Personalisation Platform enables digital marketers to engage shoppers in contextual interactions to improve the shopping experience and, ultimately, close more sales. However, there is still a need for developing machine learning methods capable of predicting consumer behaviour and predicting the best marketing strategies for different consumer behaviour and groups.

Funding

PhD full-time and part-time courses are eligible for the Government Doctoral Loan (UK and EU students only).

February start

2019/2020 entry

Home/EU/CI full-time students: £4,327 p/a*

Home/EU/CI part-time students: £2,164 p/a*

International full-time students: £15,900 p/a*

International part-time students: £7,950 p/a*

By Publication Fees 2019/2020

Members of staff: £1,610 p/a*

External candidates: £4,327 p/a*

*All fees are subject to annual increase

October start

2020/2021 entry

Home/EU/CI full-time students: £4,327 p/a**

Home/EU/CI part-time students: £2,164 p/a**

International full-time students: £16,400 p/a*

International part-time students: £8,200 p/a*

By Publication Fees 2020/2021

Members of staff: £1,680 p/a**

External candidates: £4,327 p/a*

*All fees are subject to annual increase
**This is the 2019/20 UK Research and Innovation (UKRI) maximum studentship fee; this fee will increase to the 2020/21 UKRI maximum studentship fee when UKRI announces this rate in Spring 2020.  

Entry requirements

How to apply

We’d encourage you to contact Dr Mohamed Bader (Mohamed.Bader@port.ac.uk) to discuss your interest before you apply, quoting the project code CCTS4600219.

When you're ready to apply, you can use our online application form and select ‘Computing and Creative Technologies’ as the subject area. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV. 

Our How to Apply page also offers further guidance on the PhD application process.