FREE Virtual Study Fair | 1 - 2 March | REGISTER NOW FREE Virtual Study Fair | 1 - 2 March | REGISTER NOW

Improving student retention: identifying at risk students at very early stages using machine learning

   School of Computing

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Farzad Arabikhan  No more applications being accepted  Competition Funded PhD Project (Students Worldwide)

About the Project

Applications are invited for a three year full-time (or up to six year part-time) PhD to commence in October 2023.

The PhD will be based in the School of Computing and will be supervised by Dr Farzad Arabikhan.

The work on this project could involve:

  • Extensive literature review, collecting data and developing a framework to identify the main factors in student’s drop out 
  • Develop Machine Learning/Data Mining models for the early prediction of students with low, medium and high withdrawal risk
  • Understand the differences between BME and White student performances and drop out

Project description

Student progression and non-continuation have been major challenges for universities. Disengagement mostly happens in year one and some departments such as Computing are suffering the most.

The identification and detection of at-risk students is tackled in some large measure through the personal tutoring, meetings with students and also by looking at students’ performance data - which is usually received too late. As data clearly shows, predicting potential dropouts given the highly contingent and subjective nature of personal tutoring has not been successful. Analysis of students’ performance in lower levels, background information, qualification on entry, attendance and many more factors could impact the student’s retention at the university level. Also, statistics show that more withdrawals occur around December and January time which highlights the necessity of using a centralised data-oriented system which can flag up potential at risk students at very early stages.

The project aim is to develop a framework to identify the required data and information and use Machine-Learning (ML)/Data-Mining techniques for the early prediction of students with low, medium and high withdrawal risks. The predictive ML model will be developed using primary and historical data available at the University of Portsmouth. The model output will help to identify potential “at risk” students from day 1 which will help academics to provide appropriate interventions from a very early stage. 

This project will provide an opportunity to use novel techniques in machine learning to develop appropriate predictive model and the research output can be disseminated in journal and conference papers. The University of Portsmouth will also benefit from it to improve the retention rate. 

The supervision team has experience in supervising PhD students in Machine Learning/Soft Computing with several publications and knowledge expertise in the research field. They have also been involved in a number of research and KTP projects.

General admissions criteria

You'll need a good first degree from an internationally recognised university or a Master’s degree in an appropriate subject. In exceptional cases, we may consider equivalent professional experience and/or qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.

Specific candidate requirements

Data science and programming knowledge is required.

How to Apply

We encourage you to contact Dr Farzad Arabikhan ([Email Address Removed]) to discuss your interest before you apply, quoting the project code below.

When you are ready to apply, please follow the 'Apply now' link on the Computing PhD subject area page and select the link for the relevant intake. 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 offers further guidance on the PhD application process. 

When applying please quote project code:COMP7610423

Funding Notes

Candidates applying for this project may be eligible to compete for one of a small number of bursaries available; these may provide tuition fee discounts and/or a stipend. This project is also available to students who are self-funded or hold (or likely to hold) scholarships from other organisations or governments.

Open days

Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.

PhD saved successfully
View saved PhDs