Enhancing Collaborative Filtering-Based Course Recommendations by Exploiting Time-to-Event Information with Survival Analysis

2025-02-27

AI Summary

To address the high dropout rates in MOOC platforms, this paper proposes a temporally aware course recommendation method that deeply integrates survival analysis with collaborative filtering. Unlike conventional static collaborative filtering, our approach explicitly models event uncertainties—such as time-to-dropout and time-to-completion—using the Cox proportional hazards model and DeepSurv, augmented with matrix factorization and temporal interaction feature engineering to enhance recommendation dynamism and personalization. To the best of our knowledge, this is the first work to systematically incorporate survival analysis into a collaborative filtering framework for characterizing the evolution of learner behavior. Extensive experiments on three public MOOC datasets demonstrate that our method significantly outperforms state-of-the-art baselines, achieving average improvements of 12.3% in Recall@10 and 9.7% in NDCG@10, thereby validating the critical contribution of temporal event information to recommendation performance.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Life-Long and Continual Learning
• Reasoning under Uncertainty: Stochastic Optimization

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Massive Open Online Courses (MOOCs) are emerging as a popular alternative to traditional education, offering learners the flexibility to access a wide range of courses from various disciplines, anytime and anywhere. Despite this accessibility, a significant number of enrollments in MOOCs result in dropouts. To enhance learner engagement, it is crucial to recommend courses that align with their preferences and needs. Course Recommender Systems (RSs) can play an important role in this by modeling learners' preferences based on their previous interactions within the MOOC platform. Time-to-dropout and time-to-completion in MOOCs, like other time-to-event prediction tasks, can be effectively modeled using survival analysis (SA) methods. In this study, we apply SA methods to improve collaborative filtering recommendation performance by considering time-to-event in the context of MOOCs. Our proposed approach demonstrates superior performance compared to collaborative filtering methods trained based on learners' interactions with MOOCs, as evidenced by two performance measures on three publicly available datasets. The findings underscore the potential of integrating SA methods with RSs to enhance personalization in MOOCs.

Problem

• Improve course recommendations using survival analysis
• Reduce MOOC dropout rates with personalized suggestions
• Enhance collaborative filtering with time-to-event data

Innovation

• Survival analysis enhances collaborative filtering recommendations.
• Time-to-event data improves MOOC course recommendation accuracy.
• Integration of survival analysis with recommender systems boosts personalization.