Recommender Systems — Overview
Course: Recommender Systems — 2025/2026 Programme: MSc Artificial Intelligence, UvA (IRLab) Coordinators: Maarten de Rijke, Yubao Tang Lecturers: Maarten de Rijke, Yubao Tang, Clara Rus, Xiaoyu Zhang, Yuyue Zhao, Kidist Amde Mekonnen, Dominykas Seputis Lectures: June 1–5, 2026 Format: A short lecture series followed by a course project (no textbook).
Reading
- No prescribed textbook. Lectures draw in part on the Recommender Systems Handbook (Ricci, Rokach, Shapira & Kantor, 2011) and on recent papers cited per lecture.
- Each lecture note below is written to be exam-substitute complete — the slides are the only durable source, so the notes reproduce them in full.
Assessment
To fill in
This course is project-based. Add the concrete project brief, deliverables, deadlines, and grading weights here once available — administrative detail is owned by you, not auto-generated.
| Component | Weight | Notes |
|---|---|---|
| Course Project | — | details TBD by Stanisław |
Lecture Schedule
| Topic | Lecturer(s) | Date | Notes | |
|---|---|---|---|---|
| L1 | Course Overview & Introduction | de Rijke, Tang | Jun 1 | RS-L01 - Course Overview & Introduction |
| L2 | Evaluation — Beyond Accuracy | Rus | Jun 2 | RS-L02 - Evaluation Beyond Accuracy |
| L3a | Sequential Recommender Systems | Zhang | Jun 4 | RS-L03a - Sequential Recommendation Models |
| L3b | From LLMs to LRMs (Generative Rec) | Zhao | Jun 4 | RS-L03b - From LLMs to LRMs |
| L4 | Generative Recommendation | Mekonnen, Seputis | Jun 5 | RS-L04 - Generative Recommendation |
Concept Index
Key concepts covered in this course (see the Concepts/ folder).
Foundations: Recommender System · Collaborative Filtering · Neighborhood-based Collaborative Filtering · Content-Based Recommendation · Hybrid Recommendation · Matrix Factorization · Neural Collaborative Filtering · Implicit and Explicit Feedback · User-Item Interaction Matrix · Cold Start Problem · Data Sparsity · Top-N Recommendation · Negative Sampling · Bayesian Personalized Ranking (BPR)
Accuracy Evaluation: Precision at K · Recall · NDCG · MRR · MAP · Hit Rate
Beyond-Accuracy: Beyond-Accuracy Metrics · Diversity · Novelty · Serendipity · Catalog Coverage · Maximal Marginal Relevance (MMR) · Popularity Bias · Long-Tail Distribution · Filter Bubble
Fairness & Bias: Fairness in Recommendation · Position Bias · Inverse Propensity Weighting · Algorithmic Fairness · Exposure Fairness
Evaluation Methodology: B Testing · Online and Offline Evaluation
Sequential Recommendation: Sequential Recommendation · Session-based Recommendation · Markov Chain · Factorized Personalized Markov Chains (FPMC) · GRU4Rec · SASRec · BERT4Rec · Recurrent Neural Network (RNN) · Gated Recurrent Unit (GRU) · Self-Attention · Next-Item Prediction · Contrastive Learning · Transformers
LLMs & Large Recommendation Models: Generative Recommendation · LLM-based Recommendation · Large Language Models (LLM) · Large Recommendation Models (LRM) · In-Context Learning · Supervised Fine-Tuning (SFT) · Direct Preference Optimization (DPO) · LoRA · Reinforcement Learning from Human Feedback · Cross-Domain Recommendation · Scaling Laws · HSTU · OneRec
Item Tokenization & Generative Retrieval: Item Tokenization · Semantic IDs · Atomic Item IDs · RQ-VAE · TIGER · P5 · Constrained Decoding · Beam Search · Autoregressive Generation · Diffusion Models · Generative Retrieval · DSI · Approximate Nearest Neighbor · Product Quantization