Remo Hertig, Deep Radial Basis-Function Networks for Open-Set Classification, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
A problem with modern deep learning recognition systems is that they often respond to stimuli of an unknown class overly confident, but wrong. Open-set recognition highlights this behavior and provides evaluation methods to estimate the generalization capability of models beyond the classic train/test set split. In this thesis, we incorporate a Radial Basis Function (RBF) layer into deep convolutional networks to model the deep feature distribution. We evaluate such networks on standard open-set evaluation protocols and compare their performance with standard Softmax classification models. Additionally, we utilize negative training samples and compare with the Entropic Open-Set Loss Softmax extension. We show that standard deep RBF network with Gaussian activation functions does not outperform Softmax based methods in open-set recognition. We extend the RBF network in two ways, which both show increased open-set recognition performance over the baseline RBF network. Based on these results we conjecture that solely using an RBF layer for the classification sub-system of a deep neural network might not be sufficient to solve the open-set recognition problem. |
|
Shaoyan Li, Unsupervised Shape representations for 3D reconstruction, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Non-uniform rational B-Spline surfaces (NURBS surface), a kind of parametric surface, are widely used in 3D modeling. This work explores NURBS surface reconstruction via the NURBS-Diff module. The NURBS-Diff module enables NURBS surfaces differentiable using the PyTorch framework. With supervised parameters, the module reconstructs the NURBS-based point cloud efficiently. This work introduces several pipelines by utilizing the NURBS-Diff module in unsupervised cases. The unsupervised pipelines make use of supersampling methods to obtain unstructured input and propose various metrics for point cloud and surface evaluation. The baseline unsupervised method is adapted from the original supervised pipeline. An extension of the NURBS-Diff module
is also presented. The unsupervised pipelines are evaluated against the baseline. The pipelines serve as a stepping stone to further investigation into NURBS surface reconstruction based on unstructured input. |
|
Turki Alahmadi, MFExplain: An Interactive Tool for Explaining Movie Recommendations Generated with Matrix Factorization, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Recommender systems have become integral in guiding users through the overwhelming abundance of online content. As these systems assume an ever-increasing role in shaping user decisions and preferences, there is a growing demand for clarity in their decision-making processes to instill trust. Recommendation algorithms with a high degree of accuracy such as matrix factorization are highly regarded and widely adopted. Nonetheless, these algorithms tend to exhibit high complexity in their logic and architecture, rendering them challenging to explain to end-users. This issue has been recognized and many tools have presented possible solutions. Many of the implemented approaches, however, have demonstrated shortcomings due to disregarding some user-centered properties or overly concentrating on unraveling the underlying algorithmic intricacy. This work presents MFExplain, an innovative tool for explaining movie recommendations generated with matrix factorization. The tool aims to explain recommendations by relying on the provision of intuitive justifications. Leveraging interactivity and cutting-edge dimensionality reduction techniques enables the tool to also encourage exploration, allow user feedback, and foster many desirable recommender system properties that enrich the user experience. |
|
Dogan Parlak, An Open-Source Implementation of FIFA’s Enhanced Football Intelligence, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
This thesis addresses the implementation of concepts outlined in FIFA's Enhanced Football Intelligence (EFI) document through an open-source library, filling the gap with accessible implementations for these concepts. The EFI document provides descriptions for various metrics related to football performance analysis used in the FIFA World Cup 2022. Existing packages in football analytics do not fully incorporate the latest methodologies used in the FIFA World Cup 2022, essential for the creation of a source that aligns with FIFA's definitions. The implemented concepts cover possession control, phases of play, ball recovery time, line breaks, receptions behind midfield and defensive lines, defensive line height and team length, team shape, final third entries, pressure on the ball, forced turnovers, and expected goals (xG). Utilizing the explanations of these concepts, the thesis formulates a main approach and involves refinements. The level of stability varies, with methods that incorporate fewer heuristics tending to be more stable, while those that rely on a greater number of heuristics tend to be less stable. However, during implementation, limitations were encountered, including the lack of technical details and absence of FIFA's resources regarding the technology they have employed. Specifically, the lack of heuristics mentioned in the definitions of the concepts was a notable gap. Challenges were also observed, such as specific matches that are labeled as outliers due to their performance in distinct concepts. Despite these limitations and challenges, the implementation overall offers stable and accurate performance, aligned with FIFA's outcomes.
In future work, these limitations can be addressed through a comprehensive approach. Firstly, revisiting the concepts with additional information regarding their descriptions will enhance the understanding of the underlying factors. Secondly, the expansion of datasets will not only provide a broader foundation for analysis but also improve the heuristics employed, leading to enhanced accuracy and stability of the outcomes. Additionally, the application of advanced technologies, similar to those employed by FIFA, can significantly contribute to improving the reliability and effectiveness of the results. By considering these avenues, future research can overcome the identified limitations. This thesis contributes to advancing football performance analysis by addressing these challenges and provides a valuable resource for researchers, analysts, and football enthusiasts seeking to reproduce FIFA's match reports and gain insights into football performance.
Keywords: Enhanced Football Intelligence, FIFA, open-source implementation, football performance analysis, sports analytics. |
|
Alexander Wyss, DaedalusData: Exploring and Labeling of a Large High-Dimensional Unlabeled Image Dataset; Analysis of Particle Contamination in Global Operations Consumables, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
With the surge in the volume and dimensionality of large image datasets across fields such as medicine, manufacturing, and quality monitoring, there is an increased emphasis on efficiently curating these datasets.
This design study explores the challenges associated with labeling and exploring large, high-dimensional, and unlabeled image datasets.
Traditional tools prioritize either data visualization using techniques like dimensionality reduction or labeling automation using AI learning mechanisms.
This binary focus often comes at the cost of extensive labeling functionalities or comprehensive overviews, since user interaction is reduced.
This research bridges this gap by introducing DaedalusData, an interactive visual analytics approach that combines meaningful visual exploration with efficient labeling and intuitive feedback loops.
DaedalusData presents an interactive platform that enables pattern and anomaly exploration, efficient image labeling by integrating metadata, and preliminary steps toward labeling automation.
The tool was developed alongside domain experts and built for a dataset containing particle contamination in consumables at Roche Diagnostics.
As a design study this thesis, solved a real-world problem, through close collaboration with domain experts.
The study posits that merging interactivity, human expertise, and automated processes offer a promising direction for managing large image datasets, with DaedalusData serving as a foundational step. |
|
Marco Zimmermann, Performanceauswirkung der Beimischung von Emerging Markets in ein Aktienportfolio, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Diese Arbeit untersuchte, ob sich über die letzten 20 Jahre eine Beimischung der Emerging Markets in ein Aktienportfolio fortgeschrittener Volkswirtschaften gelohnt hat. Ausserdem sollten relevante Treiber der Emerging Markets Rendite identifiziert werden und deren Einfluss gemessen werden. Aus der Untersuchung resultierte, dass sich eine Beimischung über 5,10 und 15 Jahre nicht gelohnt hat, über 20 Jahre schon. Es resultierte ein signifikant positiver Einfluss der Rohstoffentwicklung und ein signifikant negativer Einfluss der Dollar Stärke. Die GDP Wachstums-
differenz zwischen Emerging Markets und Developed Markets hatte keinen signifikanten Einfluss. Das GDP-Wachstum der Emerging Markets lieferte in einem drei Variablen Modell einen signifikant positiven Einfluss. |
|
Alexander John Völker, Persönlichkeit und Investitionsentscheidungen bei Wohneigentum, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Mit dieser quantitativen empirischen Studie mit 207 Probanden wird gezeigt, dass die Big-Five-
Persönlichkeitsdimensionen einen Einfluss auf ausgewählte Kauf- und Finanzierungspräferenzen bei Wohneigentum in Deutschland ausüben, wohingegen die
Persönlichkeitsdimension ‹Eigenschaftsangst› diese Präferenzen nicht beeinflusst. Die Auswertung erfolgte mittels ‹Ordinary Least Squares›-Regressionsanalyse. Des Weiteren besteht kein Zusammenhang zwischen den Big Five und der Preisbereitschaft bei nachhaltigen Gebäudeattributen. Ausserdem wurde festgestellt, dass sich die Kauf- und
Finanzierungspräferenzen im Mittelwert länderüber-
greifend zwischen Israel und Deutschland signifikant voneinander unterscheiden. Diese Ergebnisse unter-
streichen einerseits die Bedeutung von Persönlich-
keitsdimensionen in Entscheidungsprozessen und andererseits die Notwendigkeit, auch kulturelle Faktoren in zukünftige Forschungen einzubeziehen, um
Abweichungen besser zu verstehen. |
|
Laura Hofmann, A Single-Case Study on CEO Activism and its Evaluation by News Media Around the World, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
|
|
Yoram Bielefeldt, Persistente CSR-Vermeidung: Fallstudie zur FIFA im Vorlauf der Fussball Weltmeisterschaft 2022 in Katar von 2009 bis 2022, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
|
|
David Moser, The Dynamics of Code Review: Understanding the Impact of Change Size Through Eye Tracking Analysis, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
This research utilized eye tracking technology to gain a better comprehension of the code review process. We collected data from 14 participants, ranging from inexperienced Java users to experienced Java developers and code reviewers with more than a decade of experience. By analyzing the eye tracking data, we were able to identify differences in attention patterns based on the size of the code changes and the focus on various code elements. Notably, smaller code changes received more detailed attention to specific code elements than larger ones. Our results provide useful information that can be used to improve code review processes and developer training. |
|
Wouter van Dijk, Pattern and Signal Detection using Machine Learning for Algorithmic Trading, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Predicting equity returns is a complex task in finance. This paper examines the volume profile
as a predictive tool using machine learning techniques. We process and summarize the volume
profile into features, using an XGBoost classifier to forecast stock return direction. Our approach is
validated across two equity sets, demonstrating its capability to identify high-return periods. Based
on the probability estimates, trading strategies are created and shown to be able to outperform the
benchmark on a risk-adjusted and total return basis. Overall, the results indicate the predictive
potential of the volume profile leveraged by the model. |
|
Gino Steffen, Impact of financial development on economic indicators in advanced countries in Asia, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
The relationship between economic indicators and financial development has long been a topic of
particular interest for researchers and policymakers alike. Despite extensive research in the past, the
true nature of the relationship remained unknown. The goal of this thesis is to analyze this research
question for multiple advanced Asian countries with various economic and financial indicators. The
analysis is conducted by means of ordinary least squares regression. The results reveal that many
indicators have a rather negative impact but not consistently across all countries, making it difficult
to draw a general conclusion about the observed relationship. |
|
Andrius Kirilovas, Generalizable 4D NeRF, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Representing 3 dimensional scenes as Neural Radiance Fields (NeRF) has shown impressive results for novel view synthesis. Generalizable and dynamic variations of NeRF have been studied extensively producing photorealistic results. However, a generalizable and dynamic NeRF remains a very challenging problem. An effective solution to this problem requires a large and diverse dataset portraying complex subject motion. In this work we provide an end-to-end framework for generating high-quality synthetic datasets with complex and realistic human motion tracked by multiple cameras moving along pseudo random trajectories as well as multiple static cameras. |
|
Silvio Meier, Financial Literacy, Education and Career Aspirations: an internationals comparison with survey data, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
|
|
Patrick Eugster, Matthias W Uhl, Technical analysis: Novel insights on contrarian trading, European financial management, Vol. 29 (4), 2023. (Journal Article)
We analyze the predictive power of technical analysis with a novel data set based on news sentiment that allows to systematically examine a set of technical analysis indicators over an extensive time period. We do not find much statistically significant relationships with the examined indicators and future asset returns, and we almost do not find any alphas in trading strategies based on technical analysis sentiment. We find evidence for a contrarian-based hypothesis: past market returns and technical analysis sentiment are able to predict future technical analysis sentiment with a negative relationship. |
|
Stevo Pavicevic, Jerayr Haleblian, Thomas Keil, When Do Boards of Directors Contribute to Shareholder Value in Firms Targeted for Acquisition? A Group Information-Processing Perspective, Organization Science, Vol. 34 (5), 2023. (Journal Article)
We draw on group information-processing theory to investigate how target boards of directors may contribute to target value capture during the private negotiations phase in acquisitions. We view target boards as information-processing groups and private negotiations as information-processing tasks. We argue that target board meeting frequency is associated with increased processing—gathering, sharing, and analyzing—of acquisition-related information, which improves target bargaining and, ultimately, target value capture. We further posit that this value-enhancing effect of target board meeting frequency is more pronounced when target board composition improves the ability of target boards to process acquisition-related information. Finally, we expect that meeting frequency is more consequential for target bargaining and value capture when acquisition complexity imposes high information-processing demands on the target boards during private negotiations. Empirical evidence from a sample of acquisitions of publicly listed firms in the United States offers support for our group information-processing perspective on board contribution to shareholder value in firms targeted for acquisition. |
|
Mateusz Dolata, Gerhard Schwabe, What is the metaverse and who seeks to define it? Mapping the site of social construction, Journal of Information Technology, Vol. 38 (3), 2023. (Journal Article)
The Metaverse has become a buzz-phrase among tech businesses. Facebook's rebranding to Meta is symptomatic of this. Many firms and other actors are trying to shape visions of the Metaverse, leading to confusion about the term's meaning. We use social construction of technology (SCOT) theory to disentangle the conflicting notions proposing that what the Metaverse is and will become relies on the collective sensemaking processes. We point out similarities and differences between various concepts presented in the public media and link them to individual actors' monetary, political, or social motives. We describe the tensions that occur because of the conflicting interests. As the Metaverse is an emerging phenomenon, opportunities exist to reorient it toward humanist values rather than singular interests. However, the complexity of the social processes that shape the Metaverse requires a considerate approach rather than premature conclusions about the Metaverse’s characteristics. The analysis presents the Metaverse as a new, continually evolving sociotechnical phenomenon, and calls for research that explores it as a dynamic, moving target. |
|
Christian Ewerhart, Sheng Li, Imposing choice on the uninformed: the case of dynamic currency conversion, Journal of Banking and Finance, Vol. 154, 2023. (Journal Article)
Over the course of the past two decades, it has become a common experience for consumers authorizing an international transaction via credit card to be invited to choose the currency in which they wish the transaction to be executed. While this choice, made feasible by a technology known as dynamic currency conversion (DCC) , seems to foster competition, we argue that the opposite is the case. In fact, the unique pure-strategy equilibrium in a natural fee-setting game, with uninformed and possibly inattentive consumers, turns out to be highly asymmetric, entailing fees for the service provider that persistently exceed the monopoly level. Although losses in welfare may be substantial, a regulatory solution is unlikely to come about due to a global free-rider problem. |
|
Guido Matias Cortes, Nir Jaimovich, Henry E Siu, The growing importance of social tasks in high-paying occupations: implications for sorting, Journal of Human Resources, Vol. 58 (5), 2023. (Journal Article)
We document that, since 1980, higher paying occupations in the US have experienced increases in the importance of tasks requiring social skills compared to lower paying ones. Economic theory indicates that the occupational sorting of workers depends on their comparative advantage in performing occupational tasks. Hence, changes in the relative importance of tasks across occupations change sorting. We document that the increasing relative importance of social tasks in high-paying occupations can account for an important fraction of the increased sorting of women relative to men towards these occupations over recent decades. |
|
Carlos Alos-Ferrer, Michele Garagnani, Part-time Bayesians: incentives and behavioral heterogeneity in belief updating, Management Science, Vol. 69 (9), 2023. (Journal Article)
Decisions in management and finance rely on information that often includes win-lose feedback (e.g., gains and losses, success and failure). Simple reinforcement then suggests to blindly repeat choices if they led to success in the past and change them otherwise, which might conflict with Bayesian updating of beliefs. We use finite mixture models and hidden Markov models, adapted from machine learning, to uncover behavioral heterogeneity in the reliance on difference behavioral rules across and within individuals in a belief-updating experiment. Most decision makers rely both on Bayesian updating and reinforcement. Paradoxically, an increase in incentives increases the reliance on reinforcement because the win-lose cues become more salient. |
|