A framework for identifying the most likely successful underprivileged tertiary bursary applicants

[摘要] ENGLISH ABSTRACT: A number of non-governmental organisations (NGOs) are mandated to assist in the removal of financial barriers preventing underprivileged, prospective students from enrolling for tertiarystudies, by managing the provision of bursaries to promising individuals. These NGOs are,however, often overwhelmed by the number of bursary applications they receive. In order toselect the best applicants, very basic and sometimes unjustifiable methods involving weightedcriteria are used in industry. A scientifically justifiable decision support system (DSS) frameworkis instead proposed in this thesis for aiding NGOs in this selection process.This framework is capable of both predicting the tertiary study (success or failure) outcomeand ranking of bursary applicants in terms of potential merit. The three main components ofthe framework are a predictive component (containing multiple statistical learning models inan ensemble manner which learn from past data and then make future outcome predictions inrespect of new applicants), an integration component (which combines the predictions made bythe aforementioned models into a single prediction for each applicant), and a ranking component(which produces a rank level for each applicant in addition to his or her combined prediction).Examples of models that are included in the predictive component include logistic regression,classification and regression trees, random forests, the C4.5 algorithm, and support vector ma-chines, while majority voting and weighted majority voting are examples of methodologies thatmay be included in the integration component. The working of the integration component isbased on weighting the various model outputs according to their predictive accuracies in respectof a holdout set. Possible methodologies that may be included in the ranking component maybe found within the realm of multi-criteria decision analysis techniques. Examples of thesetechniques are the ELimination Et Choix Traduisant la REalite III (ELECTRE III) and thePreference Ranking Organisation METHod for Enrichment Evaluations II (PROMETHEE II).In order to demonstrate the practical use of the DSS framework, it is implemented in thecontext of sample data provided by two NGO industry partners. During an assessment of theperformance of the DSS in this context, it is found that the accuracy of the combined successor failure predictions for applicants is superior to those of the individual models on a one-to-onecomparison basis. It is also found that the average overall accuracy of the combined predictionssurpasses that of the manual processes currently employed by the industry partners.The sample data are further analysed for trends of interest and to identify those variables thatseem to be best suited for predicting the tertiary success of prospective students. Surprising andperhaps counter-intuitive results are obtained, indicating that high school averages and subjectmarks are, in fact, negatively correlated to the eventual tertiary success of past students. This observationis likely due to better performing high school students gravitating to the more challenging,and potentially more prestigious, tertiary institutions, study fields, and qualification types.

[发布机构] Stellenbosch University