@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{Hofmann2022,
  author    = {Hofmann, Adrian},
  title     = {Challenges and Solution Approaches for Blockchain Technology},
  doi       = {10.25972/OPUS-28261},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-282618},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2022},
  abstract  = {The digital transformation facilitates new forms of collaboration between companies along the supply chain and between companies and consumers. Besides sharing information on centralized platforms, blockchain technology is often regarded as a potential basis for this kind of collaboration. However, there is much hype surrounding the technology due to the rising popularity of cryptocurrencies, decentralized finance (DeFi), and non-fungible tokens (NFTs). This leads to potential issues being overlooked. Therefore, this thesis aims to investigate, highlight, and address the current weaknesses of blockchain technology: Inefficient consensus, privacy, smart contract security, and scalability. First, to provide a foundation, the four key challenges are introduced, and the research objectives are defined, followed by a brief presentation of the preliminary work for this thesis. The following four parts highlight the four main problem areas of blockchain. Using big data analytics, we extracted and analyzed the blockchain data of six major blockchains to identify potential weaknesses in their consensus algorithm. To improve smart contract security, we classified smart contract functionalities to identify similarities in structure and design. The resulting taxonomy serves as a basis for future standardization efforts for security-relevant features, such as safe math functions and oracle services. To challenge privacy assumptions, we researched consortium blockchains from an adversary role. We chose four blockchains with misconfigured nodes and extracted as much information from those nodes as possible. Finally, we compared scalability solutions for blockchain applications and developed a decision process that serves as a guideline to improve the scalability of their applications. Building on the scalability framework, we showcase three potential applications for blockchain technology. First, we develop a token-based approach for inter-company value stream mapping. By only relying on simple tokens instead of complex smart-contracts, the computational load on the network is expected to be much lower compared to other solutions. The following two solutions use offloading transactions and computations from the main blockchain. The first approach uses secure multiparty computation to offload the matching of supply and demand for manufacturing capacities to a trustless network. The transaction is written to the main blockchain only after the match is made. The second approach uses the concept of payment channel networks to enable high-frequency bidirectional micropayments for WiFi sharing. The host gets paid for every second of data usage through an off-chain channel. The full payment is only written to the blockchain after the connection to the client gets terminated. Finally, the thesis concludes by briefly summarizing and discussing the results and providing avenues for further research.},
  subject      = {Blockchain},
  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{Meller2020,
  author    = {Meller, Jan Maximilian},
  title     = {Data-driven Operations Management: Combining Machine Learning and Optimization for Improved Decision-making},
  doi       = {10.25972/OPUS-20604},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-206049},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2020},
  abstract  = {This dissertation consists of three independent, self-contained research papers that investigate how state-of-the-art machine learning algorithms can be used in combination with operations management models to consider high dimensional data for improved planning decisions. More specifically, the thesis focuses on the question concerning how the underlying decision support models change structurally and how those changes affect the resulting decision quality. Over the past years, the volume of globally stored data has experienced tremendous growth. Rising market penetration of sensor-equipped production machinery, advanced ways to track user behavior, and the ongoing use of social media lead to large amounts of data on production processes, user behavior, and interactions, as well as condition information about technical gear, all of which can provide valuable information to companies in planning their operations. In the past, two generic concepts have emerged to accomplish this. The first concept, separated estimation and optimization (SEO), uses data to forecast the central inputs (i.e., the demand) of a decision support model. The forecast and a distribution of forecast errors are then used in a subsequent stochastic optimization model to determine optimal decisions. In contrast to this sequential approach, the second generic concept, joint estimation-optimization (JEO), combines the forecasting and optimization step into a single optimization problem. Following this approach, powerful machine learning techniques are employed to approximate highly complex functional relationships and hence relate feature data directly to optimal decisions. The first article, "Machine learning for inventory management: Analyzing two concepts to get from data to decisions", chapter 2, examines performance differences between implementations of these concepts in a single-period Newsvendor setting. The paper first proposes a novel JEO implementation based on the random forest algorithm to learn optimal decision rules directly from a data set that contains historical sales and auxiliary data. Going forward, we analyze structural properties that lead to these performance differences. Our results show that the JEO implementation achieves significant cost improvements over the SEO approach. These differences are strongly driven by the decision problem's cost structure and the amount and structure of the remaining forecast uncertainty. The second article, "Prescriptive call center staffing", chapter 3, applies the logic of integrating data analysis and optimization to a more complex problem class, an employee staffing problem in a call center. We introduce a novel approach to applying the JEO concept that augments historical call volume data with features like the day of the week, the beginning of the month, and national holiday periods. We employ a regression tree to learn the ex-post optimal staffing levels based on similarity structures in the data and then generalize these insights to determine future staffing levels. This approach, relying on only few modeling assumptions, significantly outperforms a state-of-the-art benchmark that uses considerably more model structure and assumptions. The third article, "Data-driven sales force scheduling", chapter 4, is motivated by the problem of how a company should allocate limited sales resources. We propose a novel approach based on the SEO concept that involves a machine learning model to predict the probability of winning a specific project. We develop a methodology that uses this prediction model to estimate the "uplift", that is, the incremental value of an additional visit to a particular customer location. To account for the remaining uncertainty at the subsequent optimization stage, we adapt the decision support model in such a way that it can control for the level of trust in the predicted uplifts. This novel policy dominates both a benchmark that relies completely on the uplift information and a robust benchmark that optimizes the sum of potential profits while neglecting any uplift information. The results of this thesis show that decision support models in operations management can be transformed fundamentally by considering additional data and benefit through better decision quality respectively lower mismatch costs. The way how machine learning algorithms can be integrated into these decision support models depends on the complexity and the context of the underlying decision problem. In summary, this dissertation provides an analysis based on three different, specific application scenarios that serve as a foundation for further analyses of employing machine learning for decision support in operations management.},
  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}
}
@phdthesis{Taigel2020,
  author    = {Taigel, Fabian Michael},
  title     = {Data-driven Operations Management: From Predictive to Prescriptive Analytics},
  doi       = {10.25972/OPUS-20651},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-206514},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2020},
  abstract  = {Autonomous cars and artificial intelligence that beats humans in Jeopardy or Go are glamorous examples of the so-called Second Machine Age that involves the automation of cognitive tasks [Brynjolfsson and McAfee, 2014]. However, the larger impact in terms of increasing the efficiency of industry and the productivity of society might come from computers that improve or take over business decisions by using large amounts of available data. This impact may even exceed that of the First Machine Age, the industrial revolution that started with James Watt's invention of an efficient steam engine in the late eighteenth century. Indeed, the prevalent phrase that calls data "the new oil" indicates the growing awareness of data's importance. However, many companies, especially those in the manufacturing and traditional service industries, still struggle to increase productivity using the vast amounts of data [for Economic Co-operation and Development, 2018]. One reason for this struggle is that companies stick with a traditional way of using data for decision support in operations management that is not well suited to automated decision-making. In traditional inventory and capacity management, some data - typically just historical demand data - is used to estimate a model that makes predictions about uncertain planning parameters, such as customer demand. The planner then has two tasks: to adjust the prediction with respect to additional information that was not part of the data but still might influence demand and to take the remaining uncertainty into account and determine a safety buffer based on the underage and overage costs. In the best case, the planner determines the safety buffer based on an optimization model that takes the costs and the distribution of historical forecast errors into account; however, these decisions are usually based on a planner's experience and intuition, rather than on solid data analysis. This two-step approach is referred to as separated estimation and optimization (SEO). With SEO, using more data and better models for making the predictions would improve only the first step, which would still improve decisions but would not automize (and, hence, revolutionize) decision-making. Using SEO is like using a stronger horse to pull the plow: one still has to walk behind. The real potential for increasing productivity lies in moving from predictive to prescriptive approaches, that is, from the two-step SEO approach, which uses predictive models in the estimation step, to a prescriptive approach, which integrates the optimization problem with the estimation of a model that then provides a direct functional relationship between the data and the decision. Following Akcay et al. [2011], we refer to this integrated approach as joint estimation-optimization (JEO). JEO approaches prescribe decisions, so they can automate the decision-making process. Just as the steam engine replaced manual work, JEO approaches replace cognitive work. The overarching objective of this dissertation is to analyze, develop, and evaluate new ways for how data can be used in making planning decisions in operations management to unlock the potential for increasing productivity. In doing so, the thesis comprises five self-contained research articles that forge the bridge from predictive to prescriptive approaches. While the first article focuses on how sensitive data like condition data from machinery can be used to make predictions of spare-parts demand, the remaining articles introduce, analyze, and discuss prescriptive approaches to inventory and capacity management. All five articles consider approach that use machine learning and data in innovative ways to improve current approaches to solving inventory or capacity management problems. The articles show that, by moving from predictive to prescriptive approaches, we can improve data-driven operations management in two ways: by making decisions more accurate and by automating decision-making. Thus, this dissertation provides examples of how digitization and the Second Machine Age can change decision-making in companies to increase efficiency and productivity.},
  subject      = {Maschinelles Lernen},
  language  = {en}
}
@phdthesis{Notz2021,
  author    = {Notz, Pascal Markus},
  title     = {Prescriptive Analytics for Data-driven Capacity Management},
  doi       = {10.25972/OPUS-24042},
  url       = {http://nbn-resolving.de/urn:nbn:de:bvb:20-opus-240423},
  school      = {Universit{\"a}t W{\"u}rzburg},
  year      = {2021},
  abstract  = {Digitization and artificial intelligence are radically changing virtually all areas across business and society. These developments are mainly driven by the technology of machine learning (ML), which is enabled by the coming together of large amounts of training data, statistical learning theory, and sufficient computational power. This technology forms the basis for the development of new approaches to solve classical planning problems of Operations Research (OR): prescriptive analytics approaches integrate ML prediction and OR optimization into a single prescription step, so they learn from historical observations of demand and a set of features (co-variates) and provide a model that directly prescribes future decisions. These novel approaches provide enormous potential to improve planning decisions, as first case reports showed, and, consequently, constitute a new field of research in Operations Management (OM). First works in this new field of research have studied approaches to solving comparatively simple planning problems in the area of inventory management. However, common OM planning problems often have a more complex structure, and many of these complex planning problems are within the domain of capacity planning. Therefore, this dissertation focuses on developing new prescriptive analytics approaches for complex capacity management problems. This dissertation consists of three independent articles that develop new prescriptive approaches and use these to solve realistic capacity planning problems. The first article, "Prescriptive Analytics for Flexible Capacity Management", develops two prescriptive analytics approaches, weighted sample average approximation (wSAA) and kernelized empirical risk minimization (kERM), to solve a complex two-stage capacity planning problem that has been studied extensively in the literature: a logistics service provider sorts daily incoming mail items on three service lines that must be staffed on a weekly basis. This article is the first to develop a kERM approach to solve a complex two-stage stochastic capacity planning problem with matrix-valued observations of demand and vector-valued decisions. The article develops out-of-sample performance guarantees for kERM and various kernels, and shows the universal approximation property when using a universal kernel. The results of the numerical study suggest that prescriptive analytics approaches may lead to significant improvements in performance compared to traditional two-step approaches or SAA and that their performance is more robust to variations in the exogenous cost parameters. The second article, "Prescriptive Analytics for a Multi-Shift Staffing Problem", uses prescriptive analytics approaches to solve the (queuing-type) multi-shift staffing problem (MSSP) of an aviation maintenance provider that receives customer requests of uncertain number and at uncertain arrival times throughout each day and plans staff capacity for two shifts. This planning problem is particularly complex because the order inflow and processing are modelled as a queuing system, and the demand in each day is non-stationary. The article addresses this complexity by deriving an approximation of the MSSP that enables the planning problem to be solved using wSAA, kERM, and a novel Optimization Prediction approach. A numerical evaluation shows that wSAA leads to the best performance in this particular case. The solution method developed in this article builds a foundation for solving queuing-type planning problems using prescriptive analytics approaches, so it bridges the "worlds" of queuing theory and prescriptive analytics. The third article, "Explainable Subgradient Tree Boosting for Prescriptive Analytics in Operations Management" proposes a novel prescriptive analytics approach to solve the two capacity planning problems studied in the first and second articles that allows decision-makers to derive explanations for prescribed decisions: Subgradient Tree Boosting (STB). STB combines the machine learning method Gradient Boosting with SAA and relies on subgradients because the cost function of OR planning problems often cannot be differentiated. A comprehensive numerical analysis suggests that STB can lead to a prescription performance that is comparable to that of wSAA and kERM. The explainability of STB prescriptions is demonstrated by breaking exemplary decisions down into the impacts of individual features. The novel STB approach is an attractive choice not only because of its prescription performance, but also because of the explainability that helps decision-makers understand the causality behind the prescriptions. The results presented in these three articles demonstrate that using prescriptive analytics approaches, such as wSAA, kERM, and STB, to solve complex planning problems can lead to significantly better decisions compared to traditional approaches that neglect feature data or rely on a parametric distribution estimation.},
  subject      = {Maschinelles Lernen},
  language  = {en}
}