WS 2025/2026

Course Materials

Content of the course is available online: lecture slides, labs assignments, semestral work.

Course Language

Following on two years when NDBI021 was taught in English, this year the course will be taught in Czech.

Course Organization

The course will be divided into four main blocks: RecSys basics, user needs and preferences, advanced recommending concepts, and domain-specific recommenders. The tentative schedule is as follows:

Lectures

• Basics
  • 30.09. - Intro + basic RS
  • 07.10. - Basic RS + open problems + highlights from RecSys
• User Preferences
  • 14.10. - User feedback variants + explicit feedback
  • 21.10. - Implicit feedback + From feedback to preferences
  • 04.11. - Advanced user modeling concepts, explanations, visualizations, user control
• Advanced RS Concepts
  • 11.11. - Fairness, biases, and de-biasing
  • 18.11. - Multi-objective, multi-stakeholder RS
  • 25.11. - Group RS
  • 02.12. - Dynamic RS, Reinforcement Learning, Advanced Evaluation Concepts
  • 09.12. - Guest lecture (to be confirmed) / scalable shallow autoencoders and sparse autoencoders
• Domain-Specific RS
  • 16.12. - Intro + News domain
  • 06.01. - News + Peer recommenders + Music + E-commerce (Fashion)

Labs

• Labs 1: investigate basic usage of a selected RecSys framework (assignment) + fill-in some preference data (v1, v2, v3).
• Labs 2: investigate advanced usage of a selected RecSys framework, report findings (assignment) + fill-in some preference data (different version than during previous labs; v1, v2, v3).

Grading & Requirements

The following is required to obtain the credits:

• A research-oriented semestral work (TBD, several options are being prepared, stay tunned).
• Regular (active) participation in lectures and labs. If unable to attend regularly, please notify the instructor to discuss alternatives.

The exams will be oral with written preparation with rather broader questions to allow you to shape on what you remember - not otherwise.