Am 30. Juli 2024 wird es aufgrund einer wichtigen Datenbankaktualisierung zwischen 8 und 11 Uhr zu Serviceunterbrechungen im Bereich Student-Self-Service und Personalbedarf kommen. Vielen Dank für Ihr Verständnis.

194.035 Recommender Systems
Diese Lehrveranstaltung ist in allen zugeordneten Curricula Teil der STEOP.
Diese Lehrveranstaltung ist in mindestens einem zugeordneten Curriculum Teil der STEOP.

2024S, VU, 2.0h, 3.0EC
TUWEL

Merkmale

  • Semesterwochenstunden: 2.0
  • ECTS: 3.0
  • Typ: VU Vorlesung mit Übung
  • Format der Abhaltung: Blended Learning

Lernergebnisse

Nach positiver Absolvierung der Lehrveranstaltung sind Studierende in der Lage:

(1) Comprehend the basic concepts of recommender systems,

(2) Distinguish the differences among various recommendation methods,

(3) “Recommend” appropriate recommendation techniques and evaluation strategies when faced with a task,

(4) Implement basic recommendations methods and evaluate them over real datasets and tasks.

Inhalt der Lehrveranstaltung

  • Introduction
  • Collaborative Filtering (CF)
  • Model-based CF -- Matrix Factorization
  • Content-based Recommenders
  • Evaluation Methods
  • Sequence-aware Recommenders
  • Special Topics (e.g., Fairness, Group Recommenders, Special Domains - Tourism, Music, News)

Methoden

The programming assignments are to be done in Python using Jupyter Notebooks. A short introduction to using Jupyter Notebooks will be given. In class, there will be a discussion of the assignments, solving any problems encountered, and at then end the solutions will be overviewed.

The project is to be done in any programming language and environment. There will be dedicated lectures for the project. Also, students will be motivated (by bonus points) to actively help each other.

Prüfungsmodus

Schriftlich

Weitere Informationen

This course is an overview of the general research area of Recommender Systems. The goal of these systems is to address the information overload problem (multitude of choices) people face in everyday life. Examples include selecting news articles to read, a movie to watch, a travel destination, friends to connect with, a restaurant to dine, buying a product.

The course will introduce the basic concepts, that is, users, items, preferences, explicit/implicit feedback, and proceed to explain important tasks, such as modeling a user’s preferences and an item’s attractiveness, collecting feedback from users, predicting the degree of interest of a user for an item, evaluating effectiveness. For these tasks the course will overview the most important approaches taken, and discuss the state-of-the-art. Towards the end of the course, certain advanced specialized topics, recently being investigated by the research community, will be discussed.

The students will be asked to implement simple approaches using real-life datasets, and work on a real-case task related to current challenges in the field. 

Workload for students (in hours):

  • Preliminary Discussion: 0,5
  • Lecture Time: 13*1,5=19,5
  • Practical Part (Assignments and Project Work): 35
  • Test and Preparation for it: 20
  • Sum: 75

 

Vortragende Personen

Institut

LVA Termine

TagZeitDatumOrtBeschreibung
Di.16:00 - 18:0005.03.2024EI 8 Pötzl HS - QUER Vorlesung
Di.14:00 - 16:0012.03.2024 - 25.06.2024EI 8 Pötzl HS - QUER Vorlesung
Di.16:00 - 18:0007.05.2024EI 8 Pötzl HS - QUER Vorlesung
Di.16:00 - 18:0018.06.2024EI 8 Pötzl HS - QUER Vorlesung
Di.09:00 - 12:0025.06.2024HS 7 Schütte-Lihotzky - ARCH Vorlesung
Di.13:00 - 16:0025.06.2024EI 5 Hochenegg HS Vorlesung
Recommender Systems - Einzeltermine
TagDatumZeitOrtBeschreibung
Di.05.03.202416:00 - 18:00EI 8 Pötzl HS - QUER Vorlesung
Di.12.03.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung
Di.19.03.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung
Di.09.04.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung
Di.16.04.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung
Di.23.04.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung
Di.30.04.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung
Di.07.05.202416:00 - 18:00EI 8 Pötzl HS - QUER Vorlesung
Di.14.05.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung
Di.28.05.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung
Di.11.06.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung
Di.18.06.202416:00 - 18:00EI 8 Pötzl HS - QUER Vorlesung
Di.25.06.202409:00 - 12:00HS 7 Schütte-Lihotzky - ARCH Vorlesung
Di.25.06.202413:00 - 16:00EI 5 Hochenegg HS Vorlesung
Di.25.06.202414:00 - 16:00EI 8 Pötzl HS - QUER Vorlesung

Leistungsnachweis

The course involves individual programming assignments and a goup project as well as a final written exam.

- 4 Programming Assignments in Python using Jupyter Notebooks, where you fill in the missing code. (20% of total grade)

- 1 Project in Python partly done in groups. (40% of total grade)

- The written offline exam is closed book with open and multiple choice questions. (40% of total grade)

Prüfungen

TagZeitDatumOrtPrüfungsmodusAnmeldefristAnmeldungPrüfung
Fr.14:00 - 17:0025.10.2024EI 7 Hörsaal - ETIT schriftlich01.07.2024 00:00 - 23.10.2024 23:59in TISSExam 2nd Date

LVA-Anmeldung

Von Bis Abmeldung bis
15.02.2024 09:00 12.03.2024 23:59 31.03.2024 23:59

Curricula

StudienkennzahlVerbindlichkeitSemesterAnm.Bed.Info
066 645 Data Science Keine Angabe
066 926 Business Informatics Gebundenes Wahlfach

Literatur

Es wird kein Skriptum zur Lehrveranstaltung angeboten.

Vorkenntnisse

  • Basic knowledge of Linear Algebra, Calculus and Statistics
  • Background in Machine Learning, Information Retrieval, E-Commerce is welcome but not required
  • All necessary concepts are introduced in course
  • Content on slides alone suffice
  • Programming skills required

Vertiefende Lehrveranstaltungen

Sprache

Englisch