TU Wien:Recommender Systems and User Modeling VU (Neidhardt)

Daten

Zuordnungen

Masterstudium Business Informatics

Modul EE/COR - Enterprise Engineering Core (Gebundenes Wahlfach)

Inhalt

Foundations of Recommender Systems

• Core algorithms for recommender systems
• User modeling and preference learning
• Modeling strategies (collaborative, content-based, latent factor models)
• Practical challenges (implicit feedback, sparsity, cold start)
• Evaluation methods (accuracy, ranking, beyond-accuracy metrics)

Advanced & Responsible Recommender Systems

• Sequence-aware and session-based recommendation
• Group recommender systems
• Fairness and bias
• Generative AI & Large Language Models for recommendation
• Conversational and interactive recommender systems

Ablauf

2026S

The lectures for Recommender Systems and User Modeling (6 ECTS) and Recommender Systems (3 ECTS) were held together. Because there were more students than the capacity of the lecture room, it was decided to teach in a hybrid form (in class lecture + live stream on Lecture Tube). The lecture was only live streamed but not recorded. Presence was not mandatory during the lecture.

Students noted that it would be helpful to have access to the slides before the lecture, after that the slides were sometimes provided before the lecture.

Benötigte/Empfehlenswerte Vorkenntnisse

- Knowledge of Python is expected

- Linear Algebra (basics) expected

- Previous work with data cleaning, transformation, and training of machine learning models is helpful

Vortrag

2026S

Lecture 0: Preliminaries + Introduction to Recommender Systems

Lecture 1: User-User Collaborative Filtering

Lecture 2: Item-Item Collaborative Filtering, Implicit Feedback and Cold-Start in Collaborative Filtering, Intro to Individual Assignments, Intro to Group Project

Übungen

2026S

4 Individual Assignments in Jupyterhub that focus on the lecture topics

• Assignment 1: Step-by-step implementation of User-User CF prediction algorithm for Movielens 20M dataset

Group Projects

• Design a Use Case for a Recommender System in a Domain aligned with a UN Sustainable Development Goal
• Write a Report
• Peer Reviews
• Implement a Prototype
• Presentation

Prüfung, Benotung

noch offen

Dauer der Zeugnisausstellung

noch offen

Zeitaufwand

noch offen

Unterlagen

noch offen

Tipps

noch offen

Highlights / Lob

noch offen

Verbesserungsvorschläge / Kritik

noch offen

Materialien

Diese Seite hat noch keine Anhänge, du kannst aber neue hinzufügen.