piwik-script

Deutsch Intern
    Data Science Chair

    Recommender Systems

    At the Data Science Chair we're researching various topics within the field of recommender system. From classic applications like presenting relevant products to users in an e-commerce setting or recommending tags in our own social bookmarking system BibSonomy, to systems predicting medical examination or decisions in games. We utilize different machine learning algorithms, including deep learning in our work.

    The following staff member have open topics for practica, bachelor and master theses:

    HypTrails, Recommendation, Graph Networks for publication data, Regio Tobias Koopmann
    recommendation in ecommerce, adidas Elisabeth Fischer
    Mathematical Pattern Mining, Representation Learning, Recommender Systems Sebastian Wankerl
    Medical and Healthcare Recommendation Daniel Schlör

    In the case of excellent performance there is also the chance to submit the thesis as an article to a computer science conference and to be co-author on a scientific publication early in your studies!

    Open Topics

    06/05/2023 | Recommender Systems

    Language Modelle für Recommender Systeme

    Das Verständnis von Text ist auch ein wichtiger Bestandteil von Recommender Systemen, wenn sie auf Grundlage von textuellen Informationen Vorschläge generieren. Es hat sich gezeigt, dass Sprachmodelle/Language Modelle, die auf… more
    06/05/2023 | Recommender Systems

    Empfehlungssystem zur Unterstützung von Studienanfänger:innen in Vorkursen

    Empfehlungssysteme spielen in den letzten Jahres auch im Bereich des E-Learnings eine zunehmend größere Rolle. Dort können sie z.B. helfen, den Lernenden entsprechend ihres persönlichen Lernfortschritts und ihrer Wissenslücken… more
    06/05/2023 | Recommender Systems

    Recommendation of Co-Authorship using Hypergraph Networks

    Recently a new field of Graph Neural Networks has been revealed, which takles the field of Hypergraph networks. These networks use hyperedges, which can connect mutiple vertexes. A bibliometric dataset contains authors as vertices… more
    06/05/2023 | Recommender Systems

    Vector Representations for Institutions

    The goal of this work is to find Vector representations for institutions, as Universities. These representations can be based on geographic location, collaborations between institutions or other information. As suitable source,… more