Balancing Fined-Tuned Machine Learning Models Between Continuous and Discrete Variables - A Comprehensive Analysis Using Educational Data
Drousiotis, Efthyvoulos; Pentaliotis, Panagiotis; Shi, Lei; Cristea, Alexandra I.
Professor Alexandra Cristea email@example.com
Along with the exponential increase of students enrolling in MOOCs  arises the problem of a high student dropout rate. Researchers worldwide are interested in predicting whether students will drop out of MOOCs to prevent it. This study explores and improves ways of handling notoriously challenging continuous variables datasets, to predict dropout. Importantly, we propose a fair comparison methodology: unlike prior studies and, for the first time, when comparing various models, we use algorithms with the dataset they are intended for, thus ‘like for like.’ We use a time-series dataset with algorithms suited for time-series, and a converted discrete-variables dataset, through feature engineering, with algorithms known to handle discrete variables well. Moreover, in terms of predictive ability, we examine the importance of finding the optimal hyperparameters for our algorithms, in combination with the most effective pre-processing techniques for the data. We show that these much lighter discrete models outperform the time-series models, enabling faster training and testing. This result also holds over fine-tuning of pre-processing and hyperparameter optimisation.
Drousiotis, E., Pentaliotis, P., Shi, L., & Cristea, A. I. (2022). Balancing Fined-Tuned Machine Learning Models Between Continuous and Discrete Variables - A Comprehensive Analysis Using Educational Data. In Artificial Intelligence in Education (256-268). Springer, Cham. https://doi.org/10.1007/978-3-031-11644-5_21
|Acceptance Date||Apr 25, 2022|
|Online Publication Date||Jul 27, 2022|
|Deposit Date||Aug 31, 2022|
|Publicly Available Date||Jul 28, 2023|
|Series Title||Lecture Notes in Computer Science|
|Book Title||Artificial Intelligence in Education|
Accepted Book Chapter
The final authenticated version is available online at https://doi.org/10.1007/978-3-031-11644-5_21
You might also like
Using Deep Learning to Analyze the Psychological Effects of COVID-19
Evaluation of a hybrid AI-human recommender for CS1 instructors in a real educational scenario