# Transfer Learning using Representation Learning in Massive Open Online Courses

arXiv: https://arxiv.org/abs/1812.05043 · HTML: https://mlsanity.com/paper/1812.05043/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Dec 2018.

## Built on by (most cited first, 6 of 6)

- [Educational data mining and learning analytics: An updated survey](https://mlsanity.com/paper/2402.07956/) (2024)
- [Cross-Institutional Transfer Learning for Educational Models: Implications for Model Performance, Fairness, and Equity](https://mlsanity.com/paper/2305.00927/) (2023)
- [Meta Transfer Learning for Early Success Prediction in MOOCs](https://mlsanity.com/paper/2205.01064/) (2022)
- [Knowledge Transfer by Discriminative Pre-training for Academic Performance Prediction](https://mlsanity.com/paper/2107.04009/) (2021)
- [Transferable Student Performance Modeling for Intelligent Tutoring Systems](https://mlsanity.com/paper/2202.03980/) (2022)
- [Improving the portability of predicting students performance models by using ontologies](https://mlsanity.com/paper/2410.07358/) (2024)

## Abstract (arXiv)

In a Massive Open Online Course (MOOC), predictive models of student behavior can support multiple aspects of learning, including instructor feedback and timely intervention. Ongoing courses, when the student outcomes are yet unknown, must rely on models trained from the historical data of previously offered courses. It is possible to transfer models, but they often have poor prediction performance. One reason is features that inadequately represent predictive attributes common to both courses. We present an automated transductive transfer learning approach that addresses this issue. It relies on problem-agnostic, temporal organization of the MOOC clickstream data, where, for each student, for multiple courses, a set of specific MOOC event types is expressed for each time unit. It consists of two alternative transfer methods based on representation learning with auto-encoders: a passive approach using transductive principal component analysis and an active approach that uses a correlation alignment loss term. With these methods, we investigate the transferability of dropout prediction across similar and dissimilar MOOCs and compare with known methods. Results show improved model transferability and suggest that the methods are capable of automatically learning a feature representation that expresses common predictive characteristics of MOOCs.