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 Data Science Chair since I recieved my Master's Degree in Computer Science from the University of Würzburg in early 2019. I have worked in the past on investigating the explainable detection of anomalous and fraudulent behavior in ERP (Enterprise Resource Planning) systems in the DeepScan project. As part of the AI@Knauf project, I am currently working on integrating machine learning approaches into industrial manufacturing processes.

My research focus is the domain of explainable artificial intelligence (XAI). Here I work on providing intuitive explanations for decisions from complex anomaly detection approaches.

Teaching

Open Bachelor/Master Thesis: I have several possible thesis topics available here

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

2023[ to top ]

Tritscher, J., Krause, A., Hotho, A. (2023) Feature relevance XAI in anomaly detection: Reviewing approaches and challenges, Frontiers in Artificial Intelligence, 6, available: https://doi.org/10.3389/frai.2023.1099521.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
With complexity of artificial intelligence systems increasing continuously in past years, studies to explain these complex systems have grown in popularity. While much work has focused on explaining artificial intelligence systems in popular domains such as classification and regression, explanations in the area of anomaly detection have only recently received increasing attention from researchers. In particular, explaining singular model decisions of a complex anomaly detector by highlighting which inputs were responsible for a decision, commonly referred to as local post-hoc feature relevance, has lately been studied by several authors. In this paper, we systematically structure these works based on their access to training data and the anomaly detection model, and provide a detailed overview of their operation in the anomaly detection domain. We demonstrate their performance and highlight their limitations in multiple experimental showcases, discussing current challenges and opportunities for future work in feature relevance XAI for anomaly detection.

@article{tritscher2023feature, abstract = {With complexity of artificial intelligence systems increasing continuously in past years, studies to explain these complex systems have grown in popularity. While much work has focused on explaining artificial intelligence systems in popular domains such as classification and regression, explanations in the area of anomaly detection have only recently received increasing attention from researchers. In particular, explaining singular model decisions of a complex anomaly detector by highlighting which inputs were responsible for a decision, commonly referred to as local post-hoc feature relevance, has lately been studied by several authors. In this paper, we systematically structure these works based on their access to training data and the anomaly detection model, and provide a detailed overview of their operation in the anomaly detection domain. We demonstrate their performance and highlight their limitations in multiple experimental showcases, discussing current challenges and opportunities for future work in feature relevance XAI for anomaly detection.}, author = {Tritscher, Julian and Krause, Anna and Hotho, Andreas}, journal = {Frontiers in Artificial Intelligence}, keywords = {xai}, month = {feb}, title = {Feature relevance XAI in anomaly detection: Reviewing approaches and challenges}, volume = 6, year = 2023 }

2022[ to top ]

Tritscher, J., Schlör, D., Gwinner, F., Krause, A., Hotho, A. (2022) Towards Explainable Occupational Fraud Detection, Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2022, Communications in Computer and Information Science(1753), 79–96, available: https://doi.org/https://doi.org/10.1007/978-3-031-23633-4_7.
- [ BibTeX ]
- [ URL ]
@article{tritscher2022towards, author = {Tritscher, Julian and Schlör, Daniel and Gwinner, Fabian and Krause, Anna and Hotho, Andreas}, journal = {Machine Learning and Principles and Practice of Knowledge Discovery in Databases. ECML PKDD 2022}, keywords = {xai}, number = 1753, pages = {79-96}, title = {Towards Explainable Occupational Fraud Detection}, volume = {Communications in Computer and Information Science}, year = 2022 }
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.
- [ BibTeX ]
- [ URL ]
- [ Download ]
@article{tritscher2022erpData, author = {Tritscher, Julian and Gwinner, Fabian and Schlör, Daniel and Krause, Anna and Hotho, Andreas}, journal = {arxiv}, keywords = {myown}, title = {Open ERP System Data For Occupational Fraud Detection}, year = 2022 }

2021[ to top ]

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.
- [ Abstract ]
- [ BibTeX ]
- [ URL ]
- [ Download ]
Even though companies store large amounts of business data in enterprise resource planning (ERP) systems, obtaining data for financial fraud detection is prohibitively difficult due to privacy concerns and companies protecting trade secrets. One possible solution is game-based generation of synthetic ERP data, which poses the challenge of designing an environment that generates realistic ERP data and allows players to commit many different types of fraud. In this work, we design a multiplayer game that allows players to cooperatively run a fictional company, while simultaneously challenging them to maximize their personal gain. We introduce an approach for letting players explore fraud scenarios through emergent gameplay and present a prototype that may be primed with information from real world ERP systems to generate realistic data.

@article{tritscherfinancial, abstract = {Even though companies store large amounts of business data in enterprise resource planning (ERP) systems, obtaining data for financial fraud detection is prohibitively difficult due to privacy concerns and companies protecting trade secrets. One possible solution is game-based generation of synthetic ERP data, which poses the challenge of designing an environment that generates realistic ERP data and allows players to commit many different types of fraud. In this work, we design a multiplayer game that allows players to cooperatively run a fictional company, while simultaneously challenging them to maximize their personal gain. We introduce an approach for letting players explore fraud scenarios through emergent gameplay and present a prototype that may be primed with information from real world ERP systems to generate realistic data.}, author = {Tritscher, Julian and Krause, Anna and Schl{\"o}r, Daniel and Gwinner, Fabian and von Mammen, Sebastian and Hotho, Andreas}, journal = {IEE COG 2021}, keywords = {myown}, title = {A financial game with opportunities for fraud}, volume = 2021, year = 2021 }

2020[ to top ]

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, available: https://doi.org/10.1145/3365523.
- [ BibTeX ]
- [ Download ]
@article{kobs2020emotecontrolled, author = {Kobs, Konstantin and Zehe, Albin and Bernstetter, Armin and Chibane, Julian and Pfister, Jan and Tritscher, Julian and Hotho, Andreas}, journal = {ACM Transactions on Social Computing}, keywords = {sentiment}, note = {accepted but not published}, title = {Emote-Controlled: Obtaining Implicit Viewer Feedback through Emote based Sentiment Analysis on Comments of Popular Twitch.tv Channels}, year = 2020 }
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.
- [ Abstract ]
- [ BibTeX ]
- [ Download ]
Evaluating the explanations given by post-hoc XAI approaches on tabular data is a challenging prospect, since the subjective judgement of explanations of tabular relations is non trivial in contrast to e.g. the judgement of image heatmap explanations. In order to quantify XAI performance on categorical tabular data, where feature relationships can often be described by Boolean functions, we propose an evaluation setting through generation of synthetic datasets. To create gold standard explanations, we present a definition of feature relevance in Boolean functions. In the proposed setting we evaluate eight state-of-the-art XAI approaches and gain novel insights into XAI performance on categorical tabular data. We find that the investigated approaches often fail to faithfully explain even basic relationships within categorical data.

@article{tritscher2020evaluation, abstract = {Evaluating the explanations given by post-hoc XAI approaches on tabular data is a challenging prospect, since the subjective judgement of explanations of tabular relations is non trivial in contrast to e.g. the judgement of image heatmap explanations. In order to quantify XAI performance on categorical tabular data, where feature relationships can often be described by Boolean functions, we propose an evaluation setting through generation of synthetic datasets. To create gold standard explanations, we present a definition of feature relevance in Boolean functions. In the proposed setting we evaluate eight state-of-the-art XAI approaches and gain novel insights into XAI performance on categorical tabular data. We find that the investigated approaches often fail to faithfully explain even basic relationships within categorical data.}, author = {Tritscher, Julian and Ring, Markus and Schlör, Daniel and Hettinger, Lena and Hotho, Andreas}, booktitle = {International Symposium on Methodologies for Intelligent Systems}, keywords = {xai}, note = {Accepted but not published}, organization = {Springer}, title = {Evaluation of post-hoc XAI approaches through synthetic tabular data}, year = 2020 }