Prediction of school dropout risk group using Neural Network

Dropping out of school is one of the most complex and crucial problems in education, causing social, economic, political, academic and financial losses. In order to contribute to solve the situation, this paper presents the potentials of an intelligent, robust and innovative system, developed for the prediction of risk groups of student dropout, using a Fuzzy-ARTMAP Neural Network, one of the techniques of artificial intelligence, with possibility of continued learning. This study was conducted under the Federal Institute of Education, Science and Technology of Mato Grosso, with students of the Colleges of Technology in Automation and Industrial Control, Control Works, Internet Systems, Computer Networks and Executive Secretary. The results showed that the proposed system is satisfactory, with global accuracy superior to 76% and significant degree of reliability, making possible the early identification, even in the first term of the course, the group of students likely to drop out.

[1]  Vassilis Loumos,et al.  Dropout prediction in e-learning courses through the combination of machine learning techniques , 2009, Comput. Educ..

[2]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[3]  Stephen Grossberg,et al.  Competitive Learning: From Interactive Activation to Adaptive Resonance , 1987, Cogn. Sci..

[4]  Amy Rathbun,et al.  Higher Education: Gaps in Access and Persistence Study. Statistical Analysis Report. NCES 2012-046. , 2012 .

[5]  Stephen Grossberg,et al.  Fuzzy ARTMAP: A neural network architecture for incremental supervised learning of analog multidimensional maps , 1992, IEEE Trans. Neural Networks.

[6]  Stephen Grossberg,et al.  Comparative performance measures of fuzzy ARTMAP, learned vector quantization, and back propagation for handwritten character recognition , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[7]  Carlos R. Minussi,et al.  Neural network based on adaptive resonance theory with continuous training for multi-configuration transient stability analysis of electric power systems , 2011, Appl. Soft Comput..

[8]  Serge Herzog,et al.  Estimating Student Retention and Degree-Completion Time: Decision Trees and Neural Networks Vis-a-Vis Regression. , 2006 .

[9]  Stamos T. Karamouzis,et al.  An Artificial Neural Network for Predicting Student Graduation Outcomes , 2008 .

[10]  Saurabh Pal.  Mining Educational Data Using Classification to Decrease Dropout Rate of Students , 2012, ArXiv.

[11]  Rex Nettleford.  Higher Education in the Twenty-first Century : Vision and Action UNESCO , Paris , 5-9 October 1998 Thematic Debate : Mobilizing the Power of Culture , 2001 .

[12]  Stefanie DeLuca,et al.  Switching Schools , 2012 .

[13]  Stephen Grossberg,et al.  Fuzzy ART: Fast stable learning and categorization of analog patterns by an adaptive resonance system , 1991, Neural Networks.

[14]  Jeffrey A. Barnett,et al.  Computational Methods for a Mathematical Theory of Evidence , 1981, IJCAI.

[15]  S. Grossberg,et al.  A self-organizing neural network for supervised learning, recognition, and prediction , 1992, IEEE Communications Magazine.

[16]  Al Cripps,et al.  Using artificial neural nets to predict academic performance , 1996, SAC '96.

[17]  Željko Garača,et al.  Student Dropout Analysis with Application of Data Mining Methods , 2010 .

[18]  Vincent Tinto.  Dropout from Higher Education: A Theoretical Synthesis of Recent Research , 1975 .