Ongoing Projects
Sustainability-aware Event Data Engineering for Global Logistics
(In collaboration with the Professorship of Big Geospatial Data Management, HDSC, October 2026 – September 2029)
This tandem project develops the first holistic framework for sustainability-aware event data engineering to measure and optimize the environmental footprint of global logistics processes. By combining the expertise of TUM’s data science centers in Heilbronn (HDSC) and Munich (MDSI), we integrate ERP event logs with IoT, geospatial, and environmental data. This enables powerful predictive process analytics that support the data-driven and sustainable design of logistics processes.
Contact: Andrea Maldonado Hernandez
Design and Management of Business Capabilities in the Digital Transformation
(In collaboration with Schwarz Corporate Solutions KG, industry project, August 2026 – February 2027)
In the joint project with SCOS, a scientifically grounded approach to the strategic management of business capabilities is being developed and validated in practice. The project focuses on evaluating and prioritizing capabilities, developing a KPI system to assess their resilience, and analyzing existing data sources and data gaps. The results are brought together in a prototype dashboard concept that enables data-driven and transparent decision support for business capability management.
Contact: Angelo Mangione
Automotive Initiative+ – Application of Causal AI and Think Tank
(In collaboration with Audi and the Fraunhofer Institute for Industrial Engineering, industry project, April 2026 – December 2026)
Within AI+, innovative digital technologies for production and logistics are systematically investigated, further developed, and tested in concrete application scenarios. One focus is on the use of causal artificial intelligence in the press shop and test center to better understand cause-and-effect relationships in production data, identify root causes of errors, and provide robust and explainable foundations for process improvement decisions. In addition, a think tank is being established to assess emerging technological developments at an early stage with regard to their potential for production and logistics and to conceptually develop particularly promising — including disruptive “moonshot” — approaches together with relevant business units. The goal is to leverage new technologies to enable more resilient, agile, and efficient production.
Contact: Ana Costa
Development of a Domain-Specific Knowledge Graph for the Integration and Harmonization of Data Points in Production Systems
(In collaboration with Audi, industry project, December 2026 – November 2029)
In the joint project with Audi, an enterprise-wide knowledge graph is being designed to better integrate and utilize distributed and heterogeneous data across system and departmental boundaries. The project focuses on developing a shared ontology, consistent guidelines for extending the knowledge graph across business units, and an architectural concept for connecting existing source systems. This is intended to make relationships between data, systems, and processes more transparent, reduce redundancies, and create a consistent information base. The developed concepts are tested using concrete use cases and validated particularly with regard to their suitability as a foundation for data- and AI-driven applications.
Contact: Leon Bein
Completed Projects
Combining Process Mining and Reference Models for Improving Daily Practices and Regulations – Conformance Checking with Reference Models (CheR)
(In collaboration with university of Mannheim, DFG Individual Research Grant, August 2023 - March 2026)
Business processes often have to follow specific prescribed regulations, such as clinical practice guidelines in healthcare, laws and statutes in public administration, or the new hygiene rules in many different domains. For both organizational success and official audits, it is essential to know: Are we following the prescribed regulations? If we deviate, why? Should we improve employees’ training? Could the rules be adapted to be better applicable in the real world?
The CheR project combines, for the first time, techniques from reference modelling and conformance checking to compare real-life process behavior with prescribed regulations. The goal is to find and visualize the deviations between them to allow tailored training for employees, preparation of audits, or suggestions for improving either the process or the regulations in the respective domains. Several open aspects need to be targeted to allow conformance checking with reference models, including (1) supporting (semi)-automatic generation of reference models, (2) the extraction of useful event logs for this type of process mining project, (3) benchmarking of existing conformance checking methods and their possible extension, and (4) an empirical evaluation on how the CheR approach allows to leverage conformance checking with regulations, e.g., for training employees.
Contact: Finn Klessascheck
Automotive Initiative 25 – Process Mining Readiness
(In collaboration with Audi and the Fraunhofer Institute for Industrial Engineering, Industry project, April 2025 - December 2025)
Process Mining is a data-driven approach to the analysis and optimization of business processes, used to facilitate the efficiency, resilience, and sustainability of industries. However, good data quality and an appropriete ecosystem are needed to apply Process Mining. In the "Proces Mining Readiness" cluster of the Automotive Initiative 2025 , we derive preconditions and requirements for an application of Process Mining at Audi, using an example process from production and logistics. Our goal is to derive an initial plan of action and recommendations for data acquisition and usage. For this, we place special attention on data availability and quality.
Contact: Leon Bein and Ana Costa
Discovering, Analysing, and Improving Financial Decision-Making Processes with Process Mining Techniques
(In collaboration with the University of Adelaide, BayIntAn, June 2025 - December 2025)
The integration of advanced technologies, particularly artificial intelligence (AI), into financial decision-making processes has driven significant improvements in automation. However, these advancements come with challenges, especially regarding transparency and interpretability. Financial institutions face increasing pressure to ensure their decision-making processes remain efficient, compliant with policies, and transparent to regulators, stakeholders, and customers. As AI models are increasingly deployed in areas such as credit scoring and fraud detection, the demand for clear and comprehensible explanations of their outputs has become critical. Current AI methods often operate as "black boxes," which limits trust and verification capabilities for stakeholders. Process mining, a data analysis field, provides techniques to visualize and formalize workflows based on event log data. These techniques enable the analysis and optimization of business processes, such as loan approval workflows or credit evaluation algorithms. By applying process mining to AI-driven decision-making processes, financial institutions can uncover hidden dependencies, enhance transparency, and redesign their operations. With this project, we aim to establish a long-term collaboration between the Technical University of Munich (TUM) and the University of Adelaide, Australia. The goal is to research explainable AI with process mining and to apply for DAAD/DFG funding in 2026. The BayIntAn funding program supports us in working together on a first publication and to further strengthen the relationship between the universities by meeting in person.
Contact: Kerstin Andree