Prediction of the risk level of failure of higher education students using an artificial neural network model.
Article Sidebar
Main Article Content
Abstract
The desertion of undergraduate students and high academic failure rates is a problem in Ecuador's higher education institutions. If the failure rate in a subject is high, then the number of students who must retake the subject is also high. Therefore, it limits the available resources and makes the educational institutions' authorities constantly restructure physical spaces and teachers. On the other hand, educational data mining uses machine learning and deep learning techniques to analyze and model educational data to predict students' academic performance. Previous studies propose the use of different models of artificial neural networks to predict academic performance; however, these models focus on using only academic data and some students' sociodemographic data. On the contrary, in the present study, educational, sociodemographic, and economic data are considered, which were gathered through digital surveys and educational systems of a higher education institution, and a multi-layer perceptron network is proposed to predict the risk of failure of a student, which will allow students, teachers and authorities to know the risk of loss in a subject so that the corresponding actions can be taken to lower the failure rate. The proposed model reached an accuracy of approximately 88%, demonstrating good performance. Additionally, we compare the proposed model's performance with a decision tree's performance and a logistic regression model; these models obtained approximately 85% and 82% accuracy, respectively.
Downloads
Article Details
References
Baker, R. S. J. (2010). Data mining for education. International Encyclopedia of Education, 7(3), 112–118.
Bonaccorso, G. (2017). Machine learning algorithms. Packt Publishing Ltd.
Chang, H. M., & Kim, H. J. (2021). Predicting the pass probability of secondary school students taking online classes. Computers and Education, 164(December 2020), 104110. https://doi.org/10.1016/j.compedu.2020.104110
Cristianini, N., & Shawe-Taylor, J. (2000). An introduction to support vector machines and other kernel-based learning methods. Cambridge university press.
Davis, C. M., Hardin, J. M., Bohannon, T., & Oglesby, J. (2007). Data mining applications in higher education. Data Mining Methods and Applications, 123–148. https://doi.org/10.1201/b15783
Deng, Z., Zhu, X., Cheng, D., Zong, M., & Zhang, S. (2016). Efficient kNN classification algorithm for big data. Neurocomputing, 195, 143–148.
Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. MIT press.
He, K., Zhang, X., Ren, S., & Sun, J. (2015). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision, 2015 Inter, 1026–1034. https://doi.org/10.1109/ICCV.2015.123
Peña-Ayala, A. (2014). Educational data mining: A survey and a data mining-based analysis of recent works. Expert Systems with Applications, 41(4 PART 1), 1432–1462. https://doi.org/10.1016/j.eswa.2013.08.042
Roblyer, M. D., & Davis, L. (2008). Predicting success for virtual school students: Putting research-based models into practice. Online Journal of Distance Learning Administration, 11(4).
Rokach, L., & Maimon, O. (2005). Decision trees. In Data mining and knowledge discovery handbook (pp. 165–192). Springer.
Tieleman, T., & Hinton, G. (2012). Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude. COURSERA: Neural Networks for Machine Learning, 4(2), 26–31.
Zhang, C., & Ma, Y. (2012). Ensemble machine learning: methods and applications. Springer.