An Approach for Academic Success Predictive Modeling based on a Multi-objective Genetic Algorithm
Abstract
In this paper, we propose a new method of constructing machine learning models for predicting academic success. In this method, a multi-objective genetic algorithm is deployed to select explanatory variables for the predictive model as an approach that takes into account both elements of predictive performance and interpretability. By using two evaluation functions, i.e., prediction performance and the number of explanatory variables, our method can find the Pareto-optimal solution set that reflects these trade-offs. The numerical simulation results show that our method can obtain a model set that takes into account the trade-off between the accuracy and complexity of the predictive model, although there are differences in behavior depending on the academic success indices to be predicted.
References
G. Siemens and R. S. J. d. Baker, “Learning Analytics and Educational Data Mining: Towards Communication and Collaboration,” Proceedings of the 2nd International Conference on Learning Analytics and Knowledge, pp. 252-254, 2012.
A. Parnell, D. Jones, A. Wesaw, and D. C. Brooks, “Institutions’ Use of Data and Analytics for Student Success.” EDUCAUSE: Center for Analysis and Research, 2018.
J. Herman and M. Hilton, Supporting Students’ College Success: The Role of Assessment of Intrapersonal and Interpersonal Competencies. National Academies Press, 2017.
G. A. Rice and A. B. Russell, “Refocusing Student Success: Toward a Comprehensive Model,” in The Handbook of Institutional Research, R. D. Howard, G. W. McLaughlin, and W. E. Knight, Eds. John Wiley & Sons, 2012, pp. 237–255.
Central Council for Education, “Gakushi Katei Kyoiku No Kochiku Ni Mukete (Toshin),” Ministry of Education, Culture, Sports, Science and Technology, 2008. (in Japanese)
C. Brooks and C. Thompson, “Predictive Modelling in Teaching and Learning,” in Handbook of Learning Analytics, 1st ed., Alberta, Canada: Society for Learning Analytics Research, 2017, pp. 61–68.
Y. Hayashi, Y. Watanabe, H. Matsukawa, T. Matsuda, M. Tsubakimoto, S. Tateishi, and H. Yamashita, “Development of SVM based Risk Detector for Retention of University Students,” Proceedings of the 15th Annual Hawaii International Conference on Education, p. 31, January 2017.
O. Nelles, Nonlinear System Identification, Springer, 2001.
K. E. Arnold and M. D. Pistilli, “Course signals at Purdue: using learning analytics to increase student success,” Proceedings of 2nd International Conference on Learning Analytics and Knowledge, pp. 267–270, April 2012.
S. M. Jayaprakash, E. W. Moody, E. J. M. Lauria, J. R. Regan, and J. D. Baron, “Early Alert of Academically At-Risk Students: An Open Source Analytics Initiative,” Journal of Learning Analytics, vol. 1, no. 1, pp. 6–47, May 2014.
K. P. Murphy, Machine Learning: a Probabilistic Perspective, MIT Press, 2012.
T. Bäck, Evolutionary Computation, Oxford University Press, 1996.
D. E. Goldberg, Genetic Algorithms in Search, Optimization and Machine Learning, 1st ed., USA: Addison-Wesley Publishing Company, 1989.
K. Deb, Multi-Objective Optimization using Evolutionary Algorithms, New York, USA: John Wiley & Sons, 2001.
scikit-learn, “Machine Learning in Python,” 2021. [online]. Available: https://scikitlearn.org/stable/. [Accessed: March. 31, 2021].
DEAP Project, “DEAP documentation,” 2021. [online], Available: https://deap.readthedocs.io/en/master/. [Accessed: March. 31, 2021].
N. Kondo, T. Matsuda, Y. Hayashi, H. Matsukawa, M. Tsubakimoto, Y. Watanabe, S. Tateishi, and H. Yamashita, “Academic Success Prediction based on Important Student Data Selected via Multi-objective Evolutionary Computation,” Proceedings of the 9th International Congress on Advanced Applied Informatics (IIAI-AAI 2020), 2020.
