Data mining course choice sets and behaviours for target marketing of higher education
Alex D Singleton (2009). Journal of Targeting, Measurement and Analysis for Marketing, 17(3), 157-170. DOI: 10.1057/jt.2009.13
Abstract
As the higher education (HE) sector has expanded, so has the variety of courses on offer, with applicants now choosing between greater numbers of potential options. Where applications to HE are administered through centralised admission services, applicants will often make multiple initial course choices, which offers an opportunity to examine systematic groupings of interest within course choice sets, and assess whether certain types of student are more likely to make concentrated or diffuse subject selections. Utilising a national database of an entire cohort’s application behaviour, the empirical findings presented in this article indicate that there are clusters of subjects that are applied for in combination, and that certain ethnic minority, socio-economic groups and neighbourhood types are more likely to make more diffuse subject choices. This creates an information base of generalised course choice behaviours that HE institutions could utilise for targeted marketing, recruitment and selection activities, and additionally forms the basis of a decision support framework that could be implemented in a variety of online tools to help guide student courses.
Extended Summary
This research investigates how higher education applicants in the UK make course choices and whether certain demographic groups exhibit different subject selection patterns. Using data mining techniques on the complete 2004 UCAS (Universities and Colleges Admissions Service) database covering all UK higher education applications for that year, the study analysed 454,148 individual applicants and their course choices to identify systematic patterns in higher education decision-making. The research employed the Joint Academic Coding System (JACS) to categorise courses into subject groupings and created weighting schemes to account for single and multiple subject combinations across applicants’ six possible course choices. The methodology involved structured query language algorithms to examine subject associations and geodemographic analysis using neighbourhood classifications to understand how location and socio-economic factors influence choice behaviour. Key findings reveal distinct clusters of subjects that are frequently applied for in combination, with some courses like Medicine and Law showing highly concentrated application patterns where students typically apply only within those specific subject areas. Conversely, subjects like Human Geography demonstrate more diffuse patterns, with applicants spreading choices across multiple related fields. The research identified significant demographic variations in choice behaviour, finding that applicants from certain ethnic minority backgrounds, particularly Asian and Afro-Caribbean communities, tend to make more diffuse subject choices across their application portfolio. Similarly, students from lower socio-economic backgrounds and specific neighbourhood types, including deprived areas and ethnic minority communities, show greater tendency towards diverse subject selection rather than concentrated choices within single disciplines. The geodemographic analysis using the National Statistics Output Area Classification revealed economic dimensions to choice behaviour, with applicants from more deprived neighbourhoods making broader subject selections whilst those from affluent areas typically demonstrate more focused application patterns. These findings have substantial implications for higher education marketing, recruitment, and student guidance services. The research suggests that understanding these demographic patterns could enable more effective targeted recruitment, help institutions develop intelligent course recommendation systems, and support centralised clearing processes by better matching unfilled places with suitable applicants. The work contributes to widening participation efforts by providing evidence-based insights into how different groups navigate higher education choices, potentially enabling more effective support for under-represented demographics in accessing appropriate courses and reducing application inefficiencies across the sector.
Key Findings
- Data mining of UCAS applications reveals distinct subject clusters with Medicine and Law showing highly concentrated choice patterns.
- Asian and Afro-Caribbean applicants demonstrate significantly more diffuse course selection behaviour across multiple subject areas.
- Students from lower socio-economic backgrounds tend to make broader subject choices rather than concentrated applications.
- Geodemographic analysis identifies neighbourhood-level patterns that could improve targeted recruitment and student guidance systems.
- Research creates evidence base for intelligent course recommendation systems to reduce higher education application inefficiencies.
Citation
@article{singleton2009data,
author = {Alex D Singleton},
title = {Data mining course choice sets and behaviours for target marketing of higher education},
journal = {Journal of Targeting, Measurement and Analysis for Marketing},
year = {2009},
volume = {17(3)},
pages = {157-170},
doi = {10.1057/jt.2009.13}
}