Explore the current research stays and the latest publications emerging from the FIM ecosystem.
Hands-on residencies where alumni and students collaborate with global partners.
Research publications from the FIM community.
Hands-on residencies where alumni and students collaborate with global partners.
Optimization Algorithms for large electric vehicle fleets
Firsthand experiencing the Bay Area and getting to know the strong cultural differences to Germany, especially in attitudes toward risk and speed of execution. While this environment accelerates innovation, it also made me more aware of its social trade-offs.
Profile Simon Jakoby · Visiting Student ResearcherSparking Digital Innovation: A Framework for Employee and GenAI Involvement
Research discussions are highly valuable. They go in-depth relatively fast while being tough. At the Country Music Hall of Fame and Museum I recognized that musicians and start-ups share similar values: passion and hard work
Profile Manuel Sauer · Conference participantMulti-Agent Reinforcement Learning for Inventory Management
The opportunities, the network, and the people around you shape you just as much as your actual studies. That is why it is even more important to find the right balance between social life and work in order to achieve better outcomes in both the short and the long term.
Profile Jakob Ehrenhuber · Visiting ResearcherTail Risk optimized Parametric Nat Cat Insurance Instruments
Profile Marc Prinzing as Visiting ResearcherStructured Deep Reinforcement Learning for Autonomous Mobility on Demand Systems
Progress in research rarely occurs in a linear fashion. Instead, it involves working iteratively between hypothesis, implementation, and evaluation.
Profile Louis Anklam · Visiting Researchersupporting the investment team covering European financial and enterprise technology investments
Highly innovative and inspiring founders and businesses within the European technology landscape; Working alongside talented and highly motivated people pushes you towards the best version of yourself; Horse race betting can be quite addictive.
Profile Manuel Wenk · Growth Equity Summer AnalystLLMs-as-judges: can groups of LLMs identify innovative ideas
Interdisciplinarity, diversity, and global perspectives drive idea generation, knowledge exchange, and innovation - wether among researchers or LLMs.
Profile Hannes Voucko-Glockner · Visiting ResearcherUnsupervised construction of object-centric event logs for process mining using natural language processing on textual descriptions
I love to do research in an office where everyone sits together (not in home office).
Profile Alina Buss · Visiting ResearcherGlobal Forest Carbon Sequestration
It was a great opportunity to work in such a global environment.
Profile Franziska Stickling · Visiting ResearcherNavigating Data Science in the era of GenAI
The ideal location for innovative data science projects and sports in the nearby mountains.
Profile Julian Dormehl · Data Science Product Owner InternMachine Learning in Finance
International and intercultural cooperation, computer vision for financial documents, causal machine learning for cost prediction, and workflow automation in distribution audit.
Profile Tobias Plank · Finance Development InternIntegration of LLM agents in investment strategies
Gained experience in designing, conducting, and iterating on research processes, and applied LLMs plus causal discovery techniques to forecast financial fundamentals and market narratives.
Profile Luis Ganßloser · Visiting ResearcherStart-up success prediction with machine learning
Finding the right balance between free time and work leads to better outcomes on both ends.
Profile Daniel Parak · Exchange StudentControl of a Heterogeneous Mobility-on-Demand Fleet with Graph Neural Networks and Reinforcement Learning
London is a great and very liveable city; the people from Imperial are smart and welcoming, and reinforcement learning is a roller coaster.
Profile Zeno Woywood · Visiting ResearcherOptimal portfolio choice of a behavioral investor under affine GARCH models
Bringing together different perspectives and backgrounds is key to create something meaningfully new; Nothing is as precious and beautiful as nature itself
Profile Nando Ehler · Visiting ResearcherThe entrepreneurship and venture capital landscape in Latin America appears fragmented despite shared language and strong economic ties. Most local funds are in their first or second fundraising while building a sector-agnostic portfolio, with FinTech driving much of the activity. In Peru, universities encourage entrepreneurial careers, yet it is uncommon for graduates to launch start-ups immediately after finishing their studies.
Profile Anja Senkmüller · Exchange Student and Project InternI had a deep-dive into the start-up ecosystem in East Africa, learned how to conduct entrepreneurship trainings in a different cultural setting, and managed a project regarding the upskilling of young graduates.
Profile Anja Senkmüller · Start-up Coach & ConsultantRepair of data quality issues in process event logs
Profile Felix Zetzsche · Visiting ResearcherGlobal Rewards in Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems
A second opinion on research questions is invaluable, especially if it comes from a different cultural and academic background.
Profile Heiko Hoppe · Visiting ResearcherReinforcement Learning for Power Markets
Silicon Valley teaches you to be bold and pragmatic.
Profile Jochen Madler · Visiting ResearcherModeling of urban neighborhood energy systems
Collaborating with diverse experts from the IS, energy, and built environment domain enriched our project, fostering fresh and innovative perspectives.
Profile Jonathan Lersch · Visiting ResearcherBusiness Process Resilience
Deviations from the ordinary are the greatest opportunity to grow - applies to both life and processes :)
Profile Julia Hermann · Visiting ResearcherDigitally Enabled Social Inclusion
Breaking out of familiar habits and mindsets is exhausting at first, but worthwhile in the long run.
Profile Katharina Kneissel · Visiting ResearcherPerception of Venture Capitalists
Life is better when the surf is closer!
Profile Philipp Wiegand · Visiting ResearcherResearch publications from the FIM community.
Business environments are becoming increasingly complex due to the pervasiveness of digital technologies and socio-technical interactions, complicating the initiation of digital innovations. To navigate these complexities, incumbent firms draw on insights from employees working with core products or services, referred to as Employee-Driven Digital Innovation (EDDI). However, many employers face quiet quitting (e.g., 78% in Germany), leading to untapped innovation potential. Research on Generative Artificial Intelligence (GenAI) shows it can enhance employee engagement and produce higher-quality ideas more efficiently. This interview study, therefore, explores how employees and GenAI interact during ideation in incumbents. Based on current literature and semi-structured interviews with employees, managers, and researchers, an Employee-GenAI Involvement framework with three types of GenAI and employee involvement was developed. This research contributes theoretically by deepening the understanding of the initiation phase of digital innovation and practically by identifying drivers and barriers when integrating GenAI into employee-driven ideation.
View publicationWe study a sequential decision-making problem for a profit-maximizing operator of an autonomous mobility-on-demand system. Optimizing a central operator's vehicle-to-request dispatching policy requires efficient and effective fleet control strategies. To this end, we employ a multi-agent Soft Actor-Critic algorithm combined with weighted bipartite matching. We propose a novel vehicle-based algorithm architecture and adapt the critic's loss function to appropriately consider coordinated actions. Furthermore, we extend our algorithm to incorporate rebalancing capabilities. Through numerical experiments, we show that our approach outperforms state-of-the-art benchmarks by up to 12.9% for dispatching and up to 38.9% with integrated rebalancing.
View publicationAcross various sectors applications of eXplainableAI (XAI) gained momentum as the increasing black-boxedness of prevailing Machine Learning (ML) models became apparent. In parallel, Large Language Models (LLMs) significantly developed in their abilities to understand human language and complex patterns. By combining both, this paper presents a novel reference architecture for the interpretation of XAI through an interactive chatbot powered by a fine-tuned LLM. We instantiate the reference architecture in the context of State-of-Health (SoH) prediction for batteries and validate its design in multiple evaluation and demonstration rounds. The evaluation indicates that the implemented prototype enhances the human interpretability of ML, especially for users with less experience with XAI.
View publicationOrganizations today need to drive both a digital transformation and a sustainability transformation. Twin transformation (TT) puts forward the idea suggests that these transformations should be integrated to leverage synergies and optimize resource utilization. While previous research has identified novel resources necessary for TT, such as dynamic capabilities, little is known about how organizations can effectively create and exploit them. We adopt a resource orchestration lens on TT to address this shortcoming. To address this shortcoming, we adopt a resource orchestration lens on TT and analyze how organizations structure, bundle, and leverage their resources for TT. Based on 20 in-depth interviews with TT industry experts, we present the TT resource orchestration pyramid, through which we unfold the processes and sub-processes of resource orchestration for TT. Our findings enhance our understanding of TT resources and contribute to the emerging body of knowledge on how organizations can drive TT. In doing so, we also provide guidance for practitioners to better manage the complexity of TT.
View publicationWe study vehicle dispatching in autonomous mobility on demand (AMoD) systems, where a central operator assigns vehicles to customer requests or rejects these with the aim of maximizing its total profit. Recent approaches use multi-agent deep reinforcement learning (MADRL) to realize scalable yet performant algorithms, but train agents based on local rewards, which distorts the reward signal with respect to the system-wide profit, leading to lower performance. We therefore propose a novel global-rewards-based MADRL algorithm for vehicle dispatching in AMoD systems, which resolves so far existing goal conflicts between the trained agents and the operator by assigning rewards to agents leveraging a counterfactual baseline. Our algorithm shows statistically significant improvements across various settings on real-world data compared to state-of-the-art MADRL algorithms with local rewards. We further provide a structural analysis which shows that the utilization of global rewards can improve implicit vehicle balancing and demand forecasting abilities. An extended version of our paper, including an appendix, can be found at https://arxiv.org/abs/2312.08884. Our code is available at https://github.com/tumBAIS/GR-MADRL-AMoD.
View publication