Analysis of Predictive Models for Learner Performance using Synthetic Data and Regression Techniques
Keywords:
Education Data- Generators, Learners’ Performance, Predictive Models, Regression Models, Technical EducationAbstract
Timely identification of learners' performance is crucial for educators to intervene effectively before students encounter academic challenges. However, the scarcity and privacy concerns surrounding educational datasets pose significant hurdles. In this study, we investigate the efficacy of predictive models for learner performance using synthetic data and regression techniques. Our analysis focuses on a multi-source dataset from technical education, which has been expanded through synthetic data generation. Employing regression machine learning algorithms, we evaluate the prediction performance across actual, generated, and augmented datasets. Our findings indicate notable improvements with augmented datasets, achieving an R-squared coefficient of 0.8776. These results underscore the effectiveness of hybrid data approaches and advocate for the integration of synthetic data as a viable alternative, particularly in contexts where access to real data is limited. This integration holds promise for advancing educational technology and machine learning methodologies. Through comprehensive analysis of diverse data sources and the application of regression techniques on synthetic and augmented datasets, this investigation endeavors to evaluate the efficacy of predictive models concerning learner performance. Additionally, this study elucidates the potential utility of synthetic data as a viable alternative in instances where the available real dataset is limited in scale.
Downloads
References
S. J. Shabnam Ara, R. Tanuja and S. H. Manjula, "Regression-Driven Predictive Model to Estimate Learners' Performance through Multisource Data," in International Conference on Futuristic Technologies (INCOFT), Belagavi, Karnataka, India, pp. 1-6, 2023, DOI: 10.1109/INCOFT60753.2023.10425033.
I. Goodfellow et al., "Generative Adversarial Nets," arXiv preprint arXiv:1406.2661, 2014. [Online]. Available: https://arxiv.org/abs/1406.2661
M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang, "Deep learning with differential privacy," in Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016, pp. 308-318.
L. Wang et al., "A State-of-the-Art Review on Image Synthesis with Generative Adversarial Networks," IEEE Access, vol. 8, pp. 63514–63537, 2020.
V. Bindschaedler and R. Shokri, "Synthesizing Plausible Privacy-Preserving Location Traces," in 2016 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA, 2016, pp. 546-563.
A. Bethencourt-Aguilar, D. Castellanos-Nieves, J. J. Sosa-Alonso, and M. Area-Moreira, "Use of Generative Adversarial Networks (GANs) in Educational Technology Research," 2023.
L. L. Murray and J. G. Wilson, "Generating data sets for teaching the importance of regression analysis," Decision Sciences Journal of Innovative Education, vol. 19, no. 2, pp. 157-166, 2021.
S. Sarwat et al., "Predicting Students’ Academic Performance with Conditional Generative Adversarial Network and Deep SVM," Sensors, vol. 22, no. 13, p. 4834, 2022.
M. Hoq, P. Brusilovsky, and B. Akram, "Analysis of an Explainable Student Performance Prediction Model in an Introductory Programming Course," International Educational Data Mining Society, 2023.
A. Namoun and A. Alshanqiti, "Predicting student performance using data mining and learning analytics techniques: A systematic literature review," Applied Sciences, vol. 11, no. 1, p. 237, 2020.
S. D. A. Bujang et al., "Multiclass prediction model for student grade prediction using machine learning," IEEE Access, vol. 9, pp. 95608-95621, 2021.
E. Alyahyan and D. Dustegor, "Predicting academic success in higher education: literature review and best practices," International Journal of Educational Technology in Higher Education, vol. 17, pp. 1-21, 2020.
B. Flanagan, R. Majumdar, and H. Ogata, "Fine grain synthetic educational data: challenges and limitations of collaborative learning analytics," IEEE Access, vol. 10, pp. 26230-26241, 2022.
K. Alalawi, R. Athauda, and R. Chiong, "Contextualizing the current state of research on the use of machine learning for student performance prediction: A systematic literature review," Engineering Reports, vol. e12699, 2023.
N. Tomasevic, N. Gvozdenovic, and S. Vranes, "An Overview and Comparison of Supervised Data Mining Techniques for Student Exam Performance Prediction," Computers and Education, vol. 143, Article ID: 103676, 2019.
S.J. Shabnam Ara, R. Tanuja, S. H. Manjula, K.R Venugopal, “A Comprehensive Survey on Usage of Learning Analytics for Enhancing Learner's Performance in Learning Portals,” Journal of Educational Technology Systems, vol. 52, no. 2, pp: 245-73, 2023.
F. Giannakas, C. Troussas, I. Voyiatzis, C. Sgouropoulou, “A deep learning classification framework for early prediction of team-based academic performance,” Applied Soft Computing. vol. 106, pp:107355, 2021.
I. EI Guabassi, Z. Bousalem, R. Marah, and A. Qazdar, "Comparative Analysis of Supervised Machine Learning Algorithms to Build a Predictive Model for Evaluating Students’ Performance," 2021.
L. Ismail, H. Materwala, and A. Hennebelle, "Comparative Analysis of Machine Learning Models for Students’ Performance Prediction," in T. Antipova (Ed.), Advances in Digital Science, ICADS 2021, Advances in Intelligent Systems and Computing, vol. 1352, Springer, Cham, pp. 157-166, 2021.
L. Zhao, K. Chen, J. Song, X. Zhu, J, Sun, B. Caulfield, and B. Mac Namee, "Academic performance prediction based on multisource, multi-feature behavioral data," IEEE Access, vol. 9, pp. 5453-5465, 2020.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
