Behavioral Analytics and Machine Learning for Predicting Student Course Completion in E-Learning Systems

Diana Saputri Sri Wahyuningtyas; Hafiz Khoirul Zaman

doi:10.55681/primer.v2i4.361

Authors

Diana Saputri Sri Wahyuningtyas Universitas Negeri Malang
Hafiz Khoirul Zaman Universitas Negeri Malang

DOI:

https://doi.org/10.55681/primer.v2i4.361

Keywords:

Online Learning, Course Completion, Student Engagement, Behavioral Indicators, Random Forest, Learning Analytics

Abstract

Low course completion rates remain a major challenge in online learning environments, affecting the effectiveness and overall quality of educational outcomes. This study aims to predict students’ likelihood of completing online courses using behavioral indicators collected from their interactions with an e-learning platform. A quantitative approach was employed using the Random Forest classification algorithm. The dataset consisted of learner characteristics, course information, and video interaction behaviors, including watch time, pause count, skip count, and disengagement score. Data analysis followed the Knowledge Discovery in Databases (KDD) framework, which included data selection, preprocessing, transformation, modeling, and evaluation stages. The results demonstrated that the Random Forest model achieved excellent predictive performance, with an accuracy of 94.36% and an ROC AUC score of 0.9927. Feature importance analysis revealed that disengagement score and time watched were the most influential predictors of course completion. These findings indicate that behavioral indicators can effectively identify learners at risk of non-completion and support the development of adaptive learning systems. Therefore, the proposed model has the potential to enhance student retention and improve the overall effectiveness of online learning programs.

References

Bedi, A. (2023). Keep learning: Student engagement in an online environment. Online Learning, 27(2). https://doi.org/10.24059/olj.v27i2.3287

Werang, B., & Leba, S. (2022). Factors affecting student engagement in online teaching and learning: A qualitative case study. The Qualitative Report, 27(4). https://doi.org/10.46743/2160-3715/2022.5165

Luo, N., Li, H., Zhao, L., Wu, Z., & Zhang, J. (2021). Promoting student engagement in online learning through harmonious classroom environment. Asia-Pacific Education Researcher, 31. https://doi.org/10.1007/s40299-021-00606-5

Redmond, P., Alexsen, M., Maloney, S., et al.(2023). Student perceptions of online engagement. Online Learning, 27(1). https://doi.org/10.24059/olj.v27i1.3320

Nia, H., Marôco, J., She, L., et al.(2023). Student satisfaction and academic efficacy during online learning with the mediating effect of student engagement: A multi-country study. PLoS One, 18. https://doi.org/10.1371/journal.pone.0285315

Rajagopal, M., Ali, B., Priya, S., et al.(2023). Machine learning methods for online education case. In 2023 8th Int. Conf. on Science Technology Engineering and Mathematics (ICONSTEM). https://doi.org/10.1109/ICONSTEM56934.2023.10142626

Jaiswal, G., Sharma, A., & Sarup, R. (2020). Machine learning in higher education. In Handbook of Research on Emerging Trends and Applications of Machine Learning, 2020. https://doi.org/10.4018/978-1-5225-9643-1.ch002

Munir, H., Vogel, B., & Jacobsson, A. (2022). Artificial intelligence and machine learning approaches in digital education: A systematic revision. Information, 13(4). https://doi.org/10.3390/info13040203

Yildirim, Y., & Celepcikay, A. (2021). Artificial intelligence and machine learning applications in education. Eurasian J. of Higher Education, 4. https://doi.org/10.31039/ejohe.2021.4.49

Liu, L., Wang, S., Britton, T., & Abebe, R. (2023). Reimagining the machine learning life cycle to improve educational outcomes of students. Proc. Natl. Acad. Sci. U.S.A., 120. https://doi.org/10.1073/pnas.2204781120

Kuleto, V., Ilić, M., Dumangiu, M., et al.(2021). Exploring opportunities and challenges of artificial intelligence and machine learning in higher education institutions. Sustainability, 13(18). https://doi.org/10.3390/su131810424

Hilbert, S., Coors, S., Eb, K., et al.(2021). Machine learning for the educational sciences. Review of Education, 2021. https://doi.org/10.31234/OSF.IO/3HNR6

Shamir, G., & Levin, I. (2021). Teaching machine learning in elementary school. Int. J. Child-Computer Interaction, 31. https://doi.org/10.1016/j.ijcci.2021.100415

Tedre, M., Toivonen, T., Kahila, J., et al., (2021). Teaching machine learning in K–12 classroom: Pedagogical and technological trajectories for artificial intelligence education. IEEE Access, 9. https://doi.org/10.1109/ACCESS.2021.3097962

Ramadhani, R., Dayanti, I., Ramadhani, A., et al., (2022). The influence of online learning on students' level of understanding in courses of quantitative research methods KPI2 class. Palakka: Media and Islamic Communication, 2022. https://doi.org/10.30863/palakka.v3i1.2531

Navis, W. (2023). Persepsi pembelajaran daring. PSIKOSAINS (J. Penelitian dan Pemikiran Psikologi), 2023. https://doi.org/10.30587/psikosains.v18i2.5749

Toto, G., & Limone, P. (2021). Online quantitative research methods: A scoping review on education, psychological factors in e-learning, and working from home.

Velazquez, L., Atenas, B., & Castro-Palacio, J. (2022). Quantitative methods to determine the student workload: Empirical study based on digital platforms. Chaos, 32(10). https://doi.org/10.1063/5.0103719

Prestiadi, D., Arifin, I., & Bhayangkara, A. (2020). Meta-analysis of online learning implementation in learning effectiveness. In 2020 6th Int. Conf. on Education and Technology (ICET). https://doi.org/10.1109/ICET51153.2020.9276557

Batdı, V., Doğan, Y., & Talan, T. (2021). Effectiveness of online learning: A multi-complementary approach research with responses from the COVID-19 pandemic period. Interactive Learning Environments, 31. https://doi.org/10.1080/10494820.2021.1954035

Popa, D., Repanovici, A., Lupu, D., et al.(2020). Using mixed methods to understand teaching and learning in COVID-19 times. Sustainability, 12. https://doi.org/10.3390/su12208726

Martin, F., Sun, T., & Westine, C. (2020). A systematic review of research on online teaching and learning from 2009 to 2018. Computers & Education, 159. https://doi.org/10.1016/j.compedu.2020.104009

Paulsen, J., & McCormick, A. (2020). Reassessing disparities in online learner student engagement in higher education. Educ. Res., 49. https://doi.org/10.3102/0013189X19898690

Chiu, T. (2021). Student engagement in K–12 online learning amid COVID-19: A qualitative approach from a self-determination theory perspective. Interact. Learn. Environ., 31. https://doi.org/10.1080/10494820.2021.1926289