Go to JKU Homepage
Institute of Computational Perception
What's that?

Institutes, schools, other departments, and programs create their own web content and menus.

To help you better navigate the site, see here where you are at the moment.

Recommender Systems

Student Projects in Recommender Systems

Contacts (if not stated otherwise): Markus Schedl.

Remark: We are open for new proposals - if you are interested in Recommender Systems, feel free to contact us!


  • Extracting music listening intents/purposes from music-related and behavioral data for user modeling
  • Fairness of recommendation algorithms
  • Disentangled representation learning for recommendation
  • Removing unwanted bias/information in deep neural networks using information theory
  •  Debiasing deep models using Siamese neural networks
  • Debiasing graph-based models (graph neural networks)
  • Multistakeholder recommender systems
  • Multi-objective bias mitigation in recommender systems
  • Popularity bias in recommender systems
  • Explainability in recommender systems
  • Robustness of recommendation algorithms
  • Differential privacy in recommendation algorithms
  • Carbon footprint of recommender system algorithms
  • Psychology-informed recommender systems (cognition models, affect-aware, personality-aware systems)
  • Psychology-inspired sampling strategies for collaborative filtering
  • Post-processing collaborative filtering results according to psychological curiosity-arousal-model
  • Session-based recommendation
  • Sequential recommendation
  • Recommender systems based on large language models
  • Recommender systems based on diffusion models
  • Adversarial training for unlearning protected user characteristics in DNN-based RecSys
  • Autoencoders for recommender systems
  • Simulating the long-term impact of recommendation algorithms
  • Conversational recommender systems
  • Domain-specific recommender systems, e.g., music, jobs, point-of-interest, accommodation, fashion, etc.
  • User studies on bias and fairness of recommender systems