Refine
Year of publication
Document Type
- Doctoral Thesis (21)
- Part of Periodical (5)
- Article (1)
- Book (1)
Has Fulltext
- yes (28)
Is part of the Bibliography
- no (28) (show_all)
Keywords
- Supply Chain Management (6)
- Lehrstuhlbericht (5)
- Luftverkehr (4)
- Risikomanagement (4)
- Supply chain management (3)
- Air traffic (2)
- Air transport (2)
- Business plan (2)
- Container shipping (2)
- Geschäftsmodell (2)
Institute
- Kühne Foundation Endowed Chair of Logistics Management (28) (show_all)
This dissertation investigates the value of customer behavior in supply chain management through the application of (big) data analytics in demand forecasting. The use of advanced analytics in supply chain management is not novel. However, the growing expansion of data volumes provides companies with new opportunities to optimize their supply chain. Despite the rising interest from both academia and practice and the recent increase in publications in this area, empirical insights are still limited. At the same time, changes in customer expectations towards instant product delivery require companies to rethink their supply chain, where accurate demand forecasts are often at the core of enabling efficient and flexible processes. This makes the development of demand prediction models that can be used in practice especially relevant. We1 analyze the use of customer behavior in demand forecasting in three separate research papers. Leveraging data from research partners in the online fashion and construction industry, we assess the potential of the developed prediction models in three areas of application in supply chain management, namely order fulfillment, order picking, and inventory planning. In the first paper, we develop a prediction model for anticipatory shipping in the fashion industry, which predicts customers’ online purchases with the aim of shipping products in advance, and subsequently minimizing delivery times. Using various forecasting methods and data on customers’ behavior on the website, we test if, and how early, it is possible to predict online purchases. Results indicate that customer purchases are, to a certain extent, predictable, but anticipatory shipping comes at a high cost due to wrongly sent products. The second paper assesses the extent to which clickstream data can improve forecast accuracy for fashion products. Specifically, we assess which clickstream variables are most suitable for predicting demand, and identify the products that benefit most from this. Results indicate that clickstream data is especially useful for forecasting medium- and certain intermittent-demand products. A simulation of order picking for these products shows that using clickstream data in the forecast substantially decreases picking times. The third paper investigates how sequential pattern mining can be used to determine products with correlated demand, and how to leverage this as an input into forecasting for a supplier in the construction industry. We find that sequential pattern mining may be beneficial when used in combination with traditional forecasting methods, and that support vector regression models seem especially suited to forecast intermittent-demand products. An application to inventory planning shows that our developed forecasting model might reduce the company’s costs of inventory holding and lost sales by up to 6.9%. Overall, our research highlights the value of using customer behavior to enhance demand forecasting and the benefit of using improved forecasts in various applications in supply chain management.
1Referring to the authors of the respective chapters as noted at the beginning of each chapter.
Airport slot allocation
(2023)
This dissertation addresses the concept of airport slot allocation as a major regulatory directive in air transport management. In three sequential parts, today’s slot allocation procedure, addressing the assignment of time windows for departure and landing operations at coordinated airports, is being assessed and critically evaluated. The three sections evolve from the evaluation and revision of a suitable criteria set to the development and implementation of a network solution. As a key feature, a carbon emissions price including the air carriers’ CO2 emissions is being provided, serving as the allocation principle. In all three parts, explicit reference to the IATA Worldwide Slot Guidelines, representing today’s regulatory framework, is being provided, highlighting explicit deficits and drawbacks of that solution. In the first part, the Analytic Hierarchy Process (AHP), as a concept of decision making based on a comparison of criteria and alternatives, is being applied guiding the allocation decision at a single airport. In this section, a set of multiple criteria is being proposed and weighted according a set of slot coordinators’ preferences. As a key feature, the concept of Analytic Hierarchy Process (AHP) is being extended by the conduction of a Pairwise Comparison-based Preference Measurement (PCPM) representing one stage of the Analytic Hierarchy Process (AHP). In part two, the perspective of the dissertation changes from a single-point to a multiple-point allocation environment. In this part, a model is being provided that includes the allocation of slots in an airport network. As a key feature, slots are being allocated such that the two complementary cost functions are being minimized. On one hand, the developed carbon cost function includes the minimization of the carbon footprint per traveling passenger. On the other hand, the developed handling cost function is being minimized incorporating a dedicated airport perspective to the solution. In part three, the proposed model is being further extended by the incorporation of a third directive, the minimization of connection cost, related to the application of solution in a hub-and-spoke network. As a result, the study demonstrates how slot allocation can be conducted efficiently in an airport network, and how the consideration of the carbon footprint per traveling passenger serves to calculate the allocation optimum.
Flexibilität in der Logistik
(2005)
Logistik und Supply Chain Management haben sich inzwischen zu Funktionen entwickelt, die innerhalb einer globaleren Wertschöpfung entscheidende Erfolgsfaktoren für die Unternehmensführung sind. Dabei trägt die Logistik – gut gestaltet – nicht nur zur Anpassungsfähigkeit von Unternehmen bei. Sie ist in einer immer dynamischeren Umwelt auch selbst erheblichen Flexibilitätsherausforderungen ausgesetzt. Um dem
gerecht zu werden, haben sich in der Praxis verschiedenste Konzepte wie Outsourcing und Postponement etabliert. Gemessen an ihrer allgemeinen Marktdurchdringung sind demgegenüber die Potentiale von Personaldienstleistungen in Deutschland bisher nur in ersten Ansätzen realisiert worden.
Um die entsprechenden Potentiale für den Bereich der Logistik zu konkretisieren und den Grenzen des Einsatzes von Personaldienstleistungen gegenüberzustellen, wurde von der WHU – Otto Beisheim School of Management eine Untersuchung in Kooperation mit Randstad Deutschland durchgeführt. Mit fast 1.200 teilnehmenden Unternehmen, die das ganze Spektrum von Nichtnutzern bis hin zu sehr starken Nutzern von Zeitarbeit abdecken, gehört sie in der Logistik zu den größten ihrer Art.
Die Ergebnisse dieser Studie, zeigen deutlich, dass in vielen Unternehmen noch Potentiale für Flexibilitätssteigerungen und Kosteneinsparungen ungenutzt bleiben. Über alle Branchen hinweg liegt der Ist-Anteil der Zeitarbeit aktuell noch deutlich unter dem Anteil, den die Teilnehmer der Umfrage selbst als optimal betrachten. Entsprechend erhoffen sich die Unternehmen weitere Lohnkostensenkungspotentiale in Höhe von durchschnittlich acht Prozent. Darüber hinaus konnte in der Studie ein signifikanter Zusammenhang zwischen der Flexibilität der Unternehmen und deren jeweiligem Anteil von Zeitarbeitern nachgewiesen werden.
This dissertation integrates three papers on risk management in complex new product development projects (NPD) with an integrated perspective on the automotive industry. It seeks to provide a comprehensive access to the topic by highlighting the most relevant risk management aspects in NPD – processes and methods (chapter 2), organization and coordination (chapter 3) as well as culture and strategy (chapter 4).
The focus of chapter 2 lies on the identification and assessment of risks as the initial and most critical risk management steps. It illustrates the application of the analytic hierarchy process (AHP) method as an established multi-criteria decision analysis method to create transparency on the overall risk position of a selected highly complex NPD in the automotive industry. Chapter 2 confirms the AHP method as a suitable approach for stronger preventive risk management in complex NPD with stakeholders with conflicting functional perspectives. This sets the stage for chapter 3 and a subsequent consideration of organization and coordination.
Chapter 3 considers an issue of organization and coordination in complex NPD that is mainly based on the fact that the involved stakeholders have individual targets and rely on concurrent processes. The selected automotive industry example illustrates the resulting managerial challenge of balancing the overall NPD requirements such as product characteristics and development lead time (system perspective) and the targets of single stakeholders in NPD (individual perspective). The NK model as an important setting for search builds the methodical basis to solve this issue and results in optimized organizational and coordination setups.
The implications on risk management in complex NPD as a result of newly emerging NPD types in the automotive industry are subject to chapter 4. These implications are in line with profound industry changes that include changes in the requirements of customers and markets. Chapter 4 uses complexity theory and deploys the lens of complex adaptive systems (CAS) to NPD to outline the emerging NPD types and their implications on risk framing activities. An extended risk framework is derived as basis that addresses the cultural and strategic shift in the automotive industry with regard to managing risk in emerging NPD types.
Transportation is the backbone of globalization and international trade. Moving goods over long distances enables companies to access new markets and consumers to buy products from other parts of the world. Global trade is particularly driven by sea freight due to low cost and air cargo owing to its high speed, making both transport modes key for many industries. Anticipating future developments in transportation remains a black box for many companies. The logistics sector is characterized by high price uncertainty, market volatility, and product complexity. Transport is often organized manually and only based on employees’ experience, making it prone to error. Recent trends in international trade further complicate companies’ decisionmaking. Trends include changes in global demand, particularly driven by growing wealth in Asian countries, leading to shifts in freight rates on major trade lanes. The risk of supply chain disruptions, such as delays of container vessels, has also been increasing in the last few years. More frequent extreme weather events caused by climate change and higher traffic on shipping routes make on-time arrivals more challenging than ever. Recent breakthroughs in research indicate that novel data analytics-based methods can help to increase transparency in transportation by supporting the decision-making of shipping players. It has become evident that machine learning enhances forecast accuracy, which could enable companies to reduce uncertainty in their logistics. In our first study (Chapter 2), we1 analyze the container shipping industry to predict delays of vessels. With a forecast accuracy of 77%, we identify important influencing factors for shipping delays. This primarily includes the time between ports, piracy risk, demographics, weather, traffic in maritime chokepoints, and port congestion. In our second study (Chapter 3), we present what methods need to be applied to predict spot rates in container shipping. With an accuracy of 89%, our forecasts support the decision-making of various shipping players in negotiating their transportation contracts. My dissertation journey then took me to the air cargo industry in our third study (Chapter 4). By assessing the predictability of long-term air freight rates, we show that machine learning improves forecasts, especially for trade lanes with volatile and complex price trends. As a result, we achieve an accuracy of 93%, enabling air carriers and freight forwarders to increase their operating profits by 30%. By proposing prediction solutions featuring high accuracy, robustness, and applicability in practice, this dissertation demonstrates that predictive analytics enhance transparency in transportation. It is our hope that more advanced technologies, such as machine learning, will play an increasingly important role in future decision-making on transportation.
1The term “we” in this dissertation always refers to the authors of Viellechner and Spinler (2020, 2021a,b,c)
This dissertation assesses the characteristics and viability of the emerging longhaul Low Cost Carriers (LCCs). In particular, the aim is to understand their business model, evaluate the cost and revenue performance, and investigate its impact on other carriers. Existing academic literature is inconclusive about characteristics and viability of the business model. To validate its defining characteristics, 37 airlines flying on North Atlantic routes are clustered using Principal Component Analysis (PCA) and Hierarchical Cluster Analysis (HCA) along a newly constructed long-haul airline business model framework. To contribute to the evaluation of business model viability, cost differences between clusters are uncovered followed by a discussion of their sustainability. Key findings include the characterization of the emerging long-haul LCC business model and its significant differences from Full-Service Network Carrier (FSNC) and leisure carrier models. On a cluster average, 33% lower unit costs compared to FSNCs are identified, of which 24 percentage points are evaluated as sustainable. As these cost advantages over FSNCs are smaller compared to the original savings of short-/medium-haul LCCs, revenue competitiveness on the longhaul becomes more critical. To assess long-haul revenue performance, a new metric for benchmarking the revenue per equivalent flight capacity is defined. Subsequently, a revenue model combining traffic, fare, load factor, and seat data from the North Atlantic is developed to determine the revenue per flight capacity across a sample of city-pairs. The results show that LCCs earn revenue per flight capacity comparable to FSNCs on shorter long-haul routes. Key factors to compensate lower direct yields are fewer low-yield connecting passengers, sales of ancillary services, higher load factors, and significantly more passengers per aircraft. Long-haul LCC market impact, and in particular their impact on incumbents’ fare levels, has not yet been assessed and short-/medium-haul LCC-related findings cannot be readily applied. To evaluate the impact of long-haul LCC presence on the incumbents’ pricing, a stylized analytical model is proposed for hypotheses development. Subsequently, Two-Steps Least Squares (2SLS) regressions with Instrumental Variables (IVs) are performed, distinguishing between economy, premium economy, and business classes, based on a sample of North Atlantic routes. Confirming the first hypothesis, LCC presence reduces incumbents’ long-haul economy and premium economy fares by -10% and -13%, respectively, ceteris paribus. LCC presence, however, does not significantly impact long-haul business class fare levels, confirming the second hypothesis. These findings are particularly relevant as the North Atlantic market represents to date one of the remaining profit pools for North American and European legacy carriers. The findings of this research implicate that the long-haul LCC model is economically viable, at least on trunk routes with high demand. FSNC management should be aware of the rising competition and fare impact on North Atlantic routes. Potential reactions could include the de-bundling of entry fares with the option of ancillary sales even on long-haul routes, a re-evaluation of the revenue impact of low-yield connecting passengers, a focus on premium passengers, and a continuous reduction of operating costs.
The combined impact of changing global demand and supply dynamics, extensive trading and speculation as well as global recessionary fears, has led to an environment of unprecedented volatility in worldwide commodity markets. As a result, effective risk management has become an increasingly important topic on the agenda of top management in a broad range of industries. While practical evidence shows that successful firms integrate both operational decision making and financial hedging in a firm-wide, coordinated risk management strategy, this entails managerial challenges. On the one hand, quantifying a firm’s exposure to raw material cost risk necessitates a sound understanding of the stochastic commodity market dynamics. On the other hand, once the exposure to different sources of risk is understood, executives face an intricate optimization problem over their operational and financial decision variables with the ultimate goal to reduce profit variability, while maintaining attractive business opportunities.
In this thesis, the topic of operational and financial risk management is investigated from three different perspectives.
In Chapter 2, a four-factor maximal affine stochastic volatility model of commodity prices is developed, which is consistent with many stylized characteristics of storable commodity markets as well as the historical term structure of commodity futures and option prices. Based on this model, we provide new insights with respect to the structural dynamics of commodity markets and the pricing and hedging of commodity derivatives. As the stochastic model used to describe the uncertain evolution of commodity prices can have important implications also in the valuation and risk management of real assets, a realistic commodity price model is a prerequisite for the integrated risk management models outlined in the subsequent chapters of this dissertation.
Given the previously developed intuition for commodity market dynamics, we model the integrated operational and financial risk management problem of a stylized, single-product industrial firm in Chapter 3. The firm faces risk in the price of commodity inputs and price sensitive, stochastic demand. Within this setting, the firm seeks to maximize inter-temporal utility under downside risk aversion over a multi-period time horizon by dynamically choosing physical procurement volumes, unit selling prices, and a futures hedge. We provide a flexible, simulation-based optimization algorithm, which allows us to solve the firm’s decision problem under realistic, multi-factor commodity price dynamics involving uncertainty in the interest rate and convenience yield as well as stochastic volatility. Based on this model, we characterize the firm’s optimal operating policy and investigate a range of topics including: (a) the value of managerial flexibility and the economic cost of restrictive supply contracts; (b) the importance of accounting for the stochastic nature of costs, interest rates, convenience yields, and volatility in risk management; (c) parameter and estimation risk; (d) the impact of risk aversion and hedging on the distribution of cash flows; and (e) the sensitivity of expected performance to key input parameters.
As opposed to the case of a single-product firm, integrated procurement risk management in a large, multi-divisional organization does not only require the above mentioned cross-functional coordination between, for example, the purchasing, sales, and finance department but also involves a cross-divisional coordination of actions in order to effectively target the firm-wide net risk exposure. To capture the specific aspects of integrated risk management in this type of setting, we extend the above model to a two-product firm in Chapter 4. Within this model, each of the two divisions are subject to cost and demand risk, which can be respectively correlated. Moreover, we allow for dynamic cross-selling to capture the potential complementarity/substitutability of items. The firm has access to futures, call, and put options associated with each of the commodity input markets for financial hedging. Under an intertemporal mean-variance utility function, we are able to provide analytic solutions to the firm’s dynamic procurement, pricing, and financial hedging problem. Based on a complementary numerical study, we analyze the impact of risk correlations and unilateral changes in the market environment of one division on the entire firm. Moreover, we discuss the impact of hedging and risk aversion on optimal policy and assess the effectiveness of different operational and financial hedging strategies for risk reduction.
Door-to-door (D2D) air travel is gaining momentum for airlines, airports, and feeder traffic providers. The mobility industry and researchers are broadening their scope to include the entire travel chain, from origin to final destination. Intermodal mobility products are already on the market. At the same time, widespread trends affect transport service providers (as the suppliers) and passengers (regarding demand). Acquiring a better understanding of future D2D air travel trends is crucial for the mobility sector for long-term planning, product adaptation, the services provided and the pricing of these, and improvements in the passenger experience. Focusing on the European market, the overall objective of this doctoral thesis is to identify and understand the future trends of D2D air travel. It is divided into three parts; these provide different perspectives on trends and employ a range of methods that lead to results that develop from each other.
In Part One, the Delphi technique is utilized to identify future travel trends. The study considers projections of European air passengers and their requirements for their entire air travel chain, including airport access, a long-haul flight, and airport egress. The research focuses on 2035 and is based on a two-round Delphi survey involving 38 experts from the transport industry, academia, and consultants. The Delphi survey is supplemented with findings from a preliminary study, consisting of a literature review, interviews with 18 experts in the field of air travel, and a workshop attended by experts. Results reveal that digitalization and personalization will be the main drivers in 2035 and that passengers might demand value-added use of their travel time. In addition, environmentally friendly travel products are considered desirable but only somewhat probable by 2035. Passenger type, age, origins, and travel budget will still be influential factors in 2035. Based on the results from a hierarchical cluster analysis, Part One presents three possible future scenarios: (1) personalized D2D travel, (2) integrated D2D travel, and (3) the game-changer. A technical chapter elaborates on the Delphi technique and individual research steps.
Part Two explores the supply aspect and to what extent transport service providers consider strategically relevant trends. The scope of D2D air travel is adapted by applying multi-labeled text classification models to 52 corporate reports from a sample of transport service providers that operate in the European market. Trends identified in the first Delphi study and from an additional literature review are used to develop seven classes. Two prototype models are developed: a dictionary-based classifier and a supervised learning model using the multinomial naive Bayes and linear support vector machine classifiers. The latter yields the best model output, revealing which trends have a higher, medium, or lower relevance on the supply side. The results show that providers consider environmentally friendly air transport and related products to be highly relevant while disruption management, leveraging passengers’ data, and improving airport feeder traffic through innovative mobility initiatives are considered to be of medium relevance.
Part Three explores air passengers’ preferences and willingness to pay for ancillary services in the current transition into the new normal, brought about by the ongoing COVID-19 pandemic, high uncertainty, and changing market dynamics. A choice-based conjoint analysis is used to test six attributes within a hypothetical travel scenario for a long-haul one-way air trip. Choice data from 269 German business and leisure passengers are analyzed using a hierarchical Bayes estimator. Results reveal that the total ancillary service upgrade price influences passengers’ choices the most, followed by a seat upgrade for greater comfort and the CO2-compensation of a flight. Hygiene-related ancillaries bring low utilities. Female and senior passengers care more for environmentally friendly ancillaries. Confirming previous research, business passengers and frequent flyers care more for onboard comfort.
In this thesis, we(1) use operations research methods to provide insights into three areas associated with health care operations management. In Chapter 2, we use a discreteevent supply chain simulation to asses if coordination among partners is beneficial in a supply chain with the characteristics of the German pharmaceutical market. We find that the greatest cost savings and service levels could be achieved through a highly integrated collaboration although most of its impact could already be achieved through sharing point-of-sales demand information. Results suggest that coordination is most beneficial in situations where product shelf life is short and demand variation is high.
In Chapter 3 we consider quality-of-life maximizing sequences of prophylactic surgeries for female carriers of a BRCA1/2 genetic mutation, who face a significantly elevated breast and ovarian cancer risk. Using a Markov Decision Process model, we determine the optimal surgery sequence that maximizes the carrier’s expected lifetime qualityadjusted life years (QALYs). Baseline results demonstrate that a QALY-maximizing sequence recommends a bilateral mastectomy between ages 30 and 60 and bilateral salpingo-oophorectomy after age 40 for BRCA1 carriers. Surgeries are recommended later for BRCA2 carriers, as their cancer risk is lower. The model’s structural properties show that when one surgery has already been completed, there exists an optimal control limit after which performing the other surgery is always QALY-maximizing.
In Chapter 4, we develop a two-stage model for optimizing when and where to assign Ebola treatment unit (ETU) beds—across geographic regions—during an infectious disease outbreak’s early phase. The first stage includes a dynamic transmission model that forecasts occurrence of new cases at the regional level, thus capturing connectivity among regions; in this stage we introduce a coefficient for behavioral adaptation to changing epidemic conditions. The second stage includes two approaches to efficiently allocate intervention resources across affected regions. Such an allocation could have prevented up to 3,434 infections over an 18-week period during the 2014 Ebola outbreak in West Africa, a 58% improvement compared with the actual allocation.
(1) In Chapter 2, 3, and 4, the term ’we’ refers to the authors of Nohdurft & Spinler (2016), Nohdurft et al. (2016a), and Nohdurft et al. (2016b), respectively.