piwik-script

Intern
    Data Science Chair

    Julian Tritscher, M.Sc.

    Chair of Data Science (Informatik X)
    University of Würzburg
    Am Hubland
    97074 Würzburg
    Germany

    Email: tritscher@informatik.uni-wuerzburg.de

    Phone: (+49 931)  31 - 84467

    Office: Room B109 (Computer Science Building M2)

    Projects and Research Interests

    Explainable Artificial Intelligence  -  Anomaly Detection  -  Machine Learning

    I am part of the DMIR research group since I recieved my Master's Degree in Computer Science from the University of Würzburg in early 2019. As part of the BMBF founded research program DeepScan, I am investigating the explainable detection of anomalous and fraudulent behavior in ERP (Enterprise Resource Planning) systems.

    Teaching

    • Fundamentals of Algorithms and Data Structures (winter term 2020/21, winter term 2021/22, winter term 2022/23)
    • Data Mining (summer term 2019, summer term 2020)
    • Seminar "Selected Chapters from Machine Learning" (summer term 2019)

    Publications

    2022[ to top ]
    • Open ERP System Data For ...
      Tritscher, J., Gwinner, F., Schlör, D., Krause, A., Hotho, A. (2022) Open ERP System Data For Occupational Fraud Detection, arxiv, available: https://arxiv.org/abs/2206.04460.
    2021[ to top ]
    • A financial game with opp...
      Tritscher, J., Krause, A., Schl{\"o}r, D., Gwinner, F., von Mammen, S., Hotho, A. (2021) A financial game with opportunities for fraud, IEE COG 2021, 2021, available: https://ieee-cog.org/2021/assets/papers/paper_273.pdf.
    2020[ to top ]
    • Emote-Controlled: Obtaini...
      Kobs, K., Zehe, A., Bernstetter, A., Chibane, J., Pfister, J., Tritscher, J., Hotho, A. (2020) Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels, ACM Transactions on Social Computing.
    • Evaluation of post-hoc XA...
      Tritscher, J., Ring, M., Schlör, D., Hettinger, L., Hotho, A. (2020) Evaluation of post-hoc XAI approaches through synthetic tabular data, International Symposium on Methodologies for Intelligent Systems.