Comparison of methods on a model for predicting university success

Main Article Content

Jean-Philippe Vandamme
Nadine Meskens
Abdelhakim Artiba


For a long time, academic failure in the first year of university has fueled many debates. Many educational psychologists have tried to understand it and then explain it. Many statisticians have tried to predict it. Our research aims to establish a model making it possible to determine, as early as possible in the year, the group of first-year students on whom priority must be given to the educational resources available to improve the success rate. For this, we have transposed in the form of a questionnaire the hypotheses posed in many theoretical models. Then, after having collected sufficient and diverse data via this questionnaire, the objective was to extract information via statistical methods or data mining and thus allow the classification of students into three classes as homogeneous as possible. This article describes the methodology adopted, the variables that were analyzed and the methods that were used and compared. With the parallelization of the results provided by the various methods (discriminant analyzes, regressions, approximate sets, decision trees, etc.), it is possible to highlight their differences in performance. Indeed, some methods have been shown to be more effective in terms of correct prediction rates made, while others have been particularly interesting for their ability to highlight the predictors of university success.

Article Details

How to Cite
Vandamme, J.-P., Meskens, N., & Artiba, A. (2010). Comparison of methods on a model for predicting university success. The Journal of Quality in Education, 1(1), 9.


Droesbeke J.-J., Hecquet I., Wattelar C., ‘‘ La population étudiante ’’, Ellipses, 2001.

Entwistle N., ‘‘ Motivational factors in student's approaches to learning ’’, Shmeck R.R., Learning strategies and learning styles, Plenum press, 1988.

Greco S., Matarazzo B., Slowinski R., ‘‘ Rough sets theory for multicriteria decision analysis ’’, European Journal of Operational Research 129, pp 1-47, 2001.

Laurent G., Kapferer J.N., ‘‘ Les profils d’implication ’’, Recherche et applications en marketing, n°2, Paris, 1986.

Palm R., ‘‘ L’analyse discriminante décisionnelle: principes et application ’’, Notes stat. Inform. Gembloux, Vol. 99, n°4, 1999.

Parmentier P., ‘‘ La réussite des études universitaires: facteurs structurels et processuels de la performance académique en première année en médecine ’’ (thèse), Faculté de Psychologie et des Sciences de l’Éducation, Université Catholique de Louvain, 1994.

Pawlak Z., ‘‘ Rough sets: Theoretical Aspects of Reasoning about Data ’’, Kluwer academic publisher, 1991.

Quinlan, J.R., ‘‘ Discovering rules by induction from large collections of examples ’’. Ed. Expert Systems in the Micro Electronic Age, Edinburgh University Press, 1979.

Rakotomalala R., ‘‘ Graphes d'induction ’’ (thèse), Université Claude Bernard, Lyon I, 1997.

Rothschild M.L., ‘‘ Perspectives on Involvement : Current Problems and Future Directions ’’. Advances in Consumer Research, Vol.11, Washington, 1984.

Vandamme J.-Ph., Meskens N., Artiba A., ‘‘ La réussite universitaire : méthodes et outils d’analyse ’’. The first international congress on quality management education and training systems (CIMQUSEF), Rabat, 2004.

‘‘ 4eMka System - a rule system for multicriteria decision support integrating dominance relation with rough approximation ’’, Laboratory of Intelligent Decision Support Systems, Institute of Computing Science, Poznan University of Technology, 2000.

Most read articles by the same author(s)