@phdthesis{Stein2019,
  author    = {Stein, Nikolai Werner},
  title     = {Advanced Analytics in Operations Management and Information Systems: Methods and Applications},
  doi       = {10.25972/OPUS-19266},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-192668},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2019},
  abstract  = {Die digitale Transformation der Gesellschaft birgt enorme Potenziale f{\"u}r Unternehmen aus allen Sektoren. Diese verf{\"u}gen aufgrund neuer Datenquellen, wachsender Rechenleistung und verbesserter Konnektivit{\"a}t {\"u}ber rasant steigende Datenmengen. Um im digitalen Wandel zu bestehen und Wettbewerbsvorteile in Bezug auf Effizienz und Effektivit{\"a}t heben zu k{\"o}nnen m{\"u}ssen Unternehmen die verf{\"u}gbaren Daten nutzen und datengetriebene Entscheidungsprozesse etablieren. Dennoch verwendet die Mehrheit der Firmen lediglich Tools aus dem Bereich „descriptive analytics" und nur ein kleiner Teil der Unternehmen macht bereits heute von den M{\"o}glichkeiten der „predictive analytics" und „prescriptive analytics" Gebrauch. Ziel dieser Dissertation, die aus vier inhaltlich abgeschlossenen Teilen besteht, ist es, Einsatzm{\"o}glichkeiten von „prescriptive analytics" zu identifizieren. Da pr{\"a}diktive Modelle eine wesentliche Voraussetzung f{\"u}r „prescriptive analytics" sind, thematisieren die ersten beiden Teile dieser Arbeit Verfahren aus dem Bereich „predictive analytics." Ausgehend von Verfahren des maschinellen Lernens wird zun{\"a}chst die Entwicklung eines pr{\"a}diktiven Modells am Beispiel der Kapazit{\"a}ts- und Personalplanung bei einem IT-Beratungsunternehmen veranschaulicht. Im Anschluss wird eine Toolbox f{\"u}r Data Science Anwendungen entwickelt. Diese stellt Entscheidungstr{\"a}gern Richtlinien und bew{\"a}hrte Verfahren f{\"u}r die Modellierung, das Feature Engineering und die Modellinterpretation zur Verf{\"u}gung. Der Einsatz der Toolbox wird am Beispiel von Daten eines großen deutschen Industrieunternehmens veranschaulicht. Verbesserten Prognosen, die von leistungsf{\"a}higen Vorhersagemodellen bereitgestellt werden, erlauben es Entscheidungstr{\"a}gern in einigen Situationen bessere Entscheidungen zu treffen und auf diese Weise einen Mehrwert zu generieren. In vielen komplexen Entscheidungssituationen ist die Ableitungen von besseren Politiken aus zur Verf{\"u}gung stehenden Prognosen jedoch oft nicht trivial und erfordert die Entwicklung neuer Planungsalgorithmen. Aus diesem Grund fokussieren sich die letzten beiden Teile dieser Arbeit auf Verfahren aus dem Bereich „prescriptive analytics". Hierzu wird zun{\"a}chst analysiert, wie die Vorhersagen pr{\"a}diktiver Modelle in pr{\"a}skriptive Politiken zur L{\"o}sung eines „Optimal Searcher Path Problem" {\"u}bersetzt werden k{\"o}nnen. Trotz beeindruckender Fortschritte in der Forschung im Bereich k{\"u}nstlicher Intelligenz sind die Vorhersagen pr{\"a}diktiver Modelle auch heute noch mit einer gewissen Unsicherheit behaftet. Der letzte Teil dieser Arbeit schl{\"a}gt einen pr{\"a}skriptiven Ansatz vor, der diese Unsicherheit ber{\"u}cksichtigt. Insbesondere wird ein datengetriebenes Verfahren f{\"u}r die Einsatzplanung im Außendienst entwickelt. Dieser Ansatz integriert Vorhersagen bez{\"u}glich der Erfolgswahrscheinlichkeiten und die Modellqualit{\"a}t des entsprechenden Vorhersagemodells in ein „Team Orienteering Problem."},
  subject      = {Operations Management},
  language  = {en}
}
@phdthesis{Griebel2022,
  author    = {Griebel, Matthias},
  title     = {Applied Deep Learning: from Data to Deployment},
  doi       = {10.25972/OPUS-27765},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-277650},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2022},
  abstract  = {Novel deep learning (DL) architectures, better data availability, and a significant increase in computing power have enabled scientists to solve problems that were considered unassailable for many years. A case in point is the "protein folding problem", a 50-year-old grand challenge in biology that was recently solved by the DL-system AlphaFold. Other examples comprise the development of large DL-based language models that, for instance, generate newspaper articles that hardly differ from those written by humans. However, developing unbiased, reliable, and accurate DL models for various practical applications remains a major challenge - and many promising DL projects get stuck in the piloting stage, never to be completed. In light of these observations, this thesis investigates the practical challenges encountered throughout the life cycle of DL projects and proposes solutions to develop and deploy rigorous DL models. The first part of the thesis is concerned with prototyping DL solutions in different domains. First, we conceptualize guidelines for applied image recognition and showcase their application in a biomedical research project. Next, we illustrate the bottom-up development of a DL backend for an augmented intelligence system in the manufacturing sector. We then turn to the fashion domain and present an artificial curation system for individual fashion outfit recommendations that leverages DL techniques and unstructured data from social media and fashion blogs. After that, we showcase how DL solutions can assist fashion designers in the creative process. Finally, we present our award-winning DL solution for the segmentation of glomeruli in human kidney tissue images that was developed for the Kaggle data science competition HuBMAP - Hacking the Kidney. The second part continues the development path of the biomedical research project beyond the prototyping stage. Using data from five laboratories, we show that ground truth estimation from multiple human annotators and training of DL model ensembles help to establish objectivity, reliability, and validity in DL-based bioimage analyses. In the third part, we present deepflash2, a DL solution that addresses the typical challenges encountered during training, evaluation, and application of DL models in bioimaging. The tool facilitates the objective and reliable segmentation of ambiguous bioimages through multi-expert annotations and integrated quality assurance. It is embedded in an easy-to-use graphical user interface and offers best-in-class predictive performance for semantic and instance segmentation under economical usage of computational resources.},
  language  = {en}
}
@phdthesis{Oberdorf2022,
  author    = {Oberdorf, Felix},
  title     = {Design and Evaluation of Data-Driven Enterprise Process Monitoring Systems},
  doi       = {10.25972/OPUS-29853},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-298531},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2022},
  abstract  = {Increasing global competition forces organizations to improve their processes to gain a competitive advantage. In the manufacturing sector, this is facilitated through tremendous digital transformation. Fundamental components in such digitalized environments are process-aware information systems that record the execution of business processes, assist in process automation, and unlock the potential to analyze processes. However, most enterprise information systems focus on informational aspects, process automation, or data collection but do not tap into predictive or prescriptive analytics to foster data-driven decision-making. Therefore, this dissertation is set out to investigate the design of analytics-enabled information systems in five independent parts, which step-wise introduce analytics capabilities and assess potential opportunities for process improvement in real-world scenarios. To set up and extend analytics-enabled information systems, an essential prerequisite is identifying success factors, which we identify in the context of process mining as a descriptive analytics technique. We combine an established process mining framework and a success model to provide a structured approach for assessing success factors and identifying challenges, motivations, and perceived business value of process mining from employees across organizations as well as process mining experts and consultants. We extend the existing success model and provide lessons for business value generation through process mining based on the derived findings. To assist the realization of process mining enabled business value, we design an artifact for context-aware process mining. The artifact combines standard process logs with additional context information to assist the automated identification of process realization paths associated with specific context events. Yet, realizing business value is a challenging task, as transforming processes based on informational insights is time-consuming. To overcome this, we showcase the development of a predictive process monitoring system for disruption handling in a production environment. The system leverages state-of-the-art machine learning algorithms for disruption type classification and duration prediction. It combines the algorithms with additional organizational data sources and a simple assignment procedure to assist the disruption handling process. The design of such a system and analytics models is a challenging task, which we address by engineering a five-phase method for predictive end-to-end enterprise process network monitoring leveraging multi-headed deep neural networks. The method facilitates the integration of heterogeneous data sources through dedicated neural network input heads, which are concatenated for a prediction. An evaluation based on a real-world use-case highlights the superior performance of the resulting multi-headed network. Even the improved model performance provides no perfect results, and thus decisions about assigning agents to solve disruptions have to be made under uncertainty. Mathematical models can assist here, but due to complex real-world conditions, the number of potential scenarios massively increases and limits the solution of assignment models. To overcome this and tap into the potential of prescriptive process monitoring systems, we set out a data-driven approximate dynamic stochastic programming approach, which incorporates multiple uncertainties for an assignment decision. The resulting model has significant performance improvement and ultimately highlights the particular importance of analytics-enabled information systems for organizational process improvement.},
  subject      = {Operations Management},
  language  = {en}
}
@phdthesis{Hauser2020,
  author    = {Hauser, Matthias},
  title     = {Smart Store Applications in Fashion Retail},
  doi       = {10.25972/OPUS-19301},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-193017},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2020},
  abstract  = {Traditional fashion retailers are increasingly hard-pressed to keep up with their digital competitors. In this context, the re-invention of brick-and-mortar stores as smart retail environments is being touted as a crucial step towards regaining a competitive edge. This thesis describes a design-oriented research project that deals with automated product tracking on the sales floor and presents three smart fashion store applications that are tied to such localization information: (i) an electronic article surveillance (EAS) system that distinguishes between theft and non-theft events, (ii) an automated checkout system that detects customers' purchases when they are leaving the store and associates them with individual shopping baskets to automatically initiate payment processes, and (iii) a smart fitting room that detects the items customers bring into individual cabins and identifies the items they are currently most interested in to offer additional customer services (e.g., product recommendations or omnichannel services). The implementation of such cyberphysical systems in established retail environments is challenging, as architectural constraints, well-established customer processes, and customer expectations regarding privacy and convenience pose challenges to system design. To overcome these challenges, this thesis leverages Radio Frequency Identification (RFID) technology and machine learning techniques to address the different detection tasks. To optimally configure the systems and draw robust conclusions regarding their economic value contribution, beyond technological performance criteria, this thesis furthermore introduces a service operations model that allows mapping the systems' technical detection characteristics to business relevant metrics such as service quality and profitability. This analytical model reveals that the same system component for the detection of object transitions is well suited for the EAS application but does not have the necessary high detection accuracy to be used as a component of an automated checkout system.},
  subject      = {Laden},
  language  = {en}
}