Alessio Brazerol, A Point-Cloud Normal Surface Estimation Methods Comparision, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
 
Point clouds are used in various algorithms in related fields, such as Visual Computing. Some of these algorithms require high-quality normals as input. Computing these surface normals is often the job of a different algorithm. Researchers have suggested vastly different algorithms over the years. Recent work focuses on using deep learning to estimate surface normals. It is important that these normal estimation algorithms perform well, as the other algorithms rely on their quality. This means the normal estimation algorithms need to be robust against various defects, including noise, outliers and differences in sampling density. Researches have proposed different measures to evaluate these normal estimation algorithms as well as how to produce synthetic test data to test against. Synthetic test data is especially useful as it provides ground truth normals to test against and can be constructed to contain a single or multiple defects with various strengths. Because of this, synthetic models are a valuable addition to real-world test data. In this paper, we evaluate four different normal estimation algorithms. This includes three regression based and one deep learning based method. We develop a tool to execute and compare the selected normal estimation algorithms. Our goal is to use good measures and cover multiple defects with our test data. In order to do this, we test the methods against various levels of noise and outliers. We use five different synthetic point cloud models and a real-world point cloud to test against. This allows us to identify the strengths and weaknesses of the tested methods. |
|
Tanmay Chimurkar, Adapting Pre-trained Transformer Language Models for Mapping Texts on Domain-Specific Ontologies, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
 
This master thesis explores domain adaptation methods for pre-trained Large Language Models (LLMs) to map natural language mentions from a text genre onto a target domain ontology based on cosine similarity in a semantic vector space. For the thesis, the input mentions are skill requirement mentions extracted from Swiss job ad postings written in German or English, and the target domain onto which these terms have to be mapped is the European Skills, Competences, Qualifications and Occupations (ESCO) ontology. The objective of this task is to track changes in the labor market and help recruiters fill positions based on skill requirements fulfilled by candidates. The thesis explores three methods: Masked Language Modelling, Multiple Negative Ranking Loss, and binary classification method for further pre-training in order to adapt LLMs to a target domain ontology. Experiments were conducted on 15 model variants using different input data and starting models. Two gold standard datasets, one consisting of randomly selected skill requirement mentions, and the other specifically crafted from challenging cases, were used for evaluating model performance. The evaluations were created by annotating the top suggestions made by our model variants. Mean Average Precision (MAP) scores were computed based on human annotations of the suggestions, made by each model variant for each term in the gold standard datasets. MAP is used as an evaluation metric since more than one mapping might be correct or acceptable, and a good ranking of the appropriate ontology concepts can be measured via this metric. The MNR models with the hard negative sampling strategy, wherein the negative samples are taken with lexical and semantic similarities to the anchor term, and domain adaptation on both the job-ads data and the ESCO ontology data were found to be the best-performing model variants for both the English and German languages. The thesis concludes that domain adaptation on both the input texts and the target domain is beneficial for mapping mentions from the input genre onto the target domain. It also suggests that using a hard negative sampling method for creating the MNR data is beneficial compared to a random negative sampling method. |
|
Marinja Principe, Motivating effective breaks for knowledge workers with Break Scheduler, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
 
Knowledge workers generally have only a limited amount of personal resources, including energy, attention and physical capacity, to achieve tasks throughout their day. When these resources are depleted, the person can feel stressed and emotionally exhausted. Knowing how and being able to recharge personal resources is, therefore, essential. As knowledge workers often spend a large part of their day at work, it can be helpful to use time spent at work to establish tiny positive habits, which help to recharge personal resources. Several studies demonstrated that regular breaks can significantly reduce stress and physical discomfort. However, while many studies focus on identifying opportune moments to suggest breaks, they rarely consider the activities that knowledge workers pursue during the break. By the definition of resource depletion, each activity can recharge or deplete resources, depending on personal preferences, making break activities crucial for achieving beneficial breaks.
This thesis explores how the Break Scheduler approach may increase users' awareness on their personal resources and break habits and how it supports them in identifying beneficial break activities to improve their personal resources. This approach focuses on self-experimentation to improve awareness through self-reporting and nudging. Additionally, a rule-based system suggests a break schedule which is personalized by the user and will be adjusted by the Break Scheduler over the use period based on the user's self-reports. The investigation included 13 participants who used the software over one to two weeks. A total of 154 breaks were reported, as well as 143 daily reports. Each participant also answered a pre- and post-intervention questionnaire, giving valuable insights into their demographics, previous break habits, and their experience with the Break Scheduler. Overall, the findings suggest that self-reporting and nudging, such as scheduling the breaks in advance and notifications, can improve the awareness of the participant's personal resources and break habits. Additionally, the personalisation aspect of the Break Scheduler is crucial to help users to identify break activities that were successfully supporting them to recharge their personal resources. The results of this thesis offer insights into the potential of the Break Scheduler approach in supporting knowledge workers to increase their awareness on their personal resources and break habits by self-reporting and nudging and in helping them find beneficial activities to improve their personal resources. |
|
Janik Lüchinger, AI-powered Ransomware to Optimize its Impact on IoT Spectrum Sensors, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
 
This work aims to investigate the feasibility of exploiting reinforcement learning (RL) to improve the impact of ransomware on a target device while evading dynamic detection methods such as behavioral fingerprinting-based anomaly detection (AD). Given the constantly growing number of connected resource-constrained devices, such as Internet of Things (IoT) devices, and the significant rise in ransomware attacks over the past years, the importance of investigating ransomware attacks and corresponding defense approaches is evident. So far, most related research has been confined to exploring unethical artificial intelligence (AI) systems instead of analyzing the possibilities of using AI for launching optimized malware attacks.
This work covers the mentioned limitations and introduces Ransomware Optimized with AI for Resource-constrained devices (ROAR), an RL framework to hide ransomware from dynamic detection mechanisms and optimize its impact on the target device. ROAR has been deployed in a real-world IoT crowdsensing scenario, including a Raspberry Pi 4 as a spectrum sensor. The Raspberry Pi was infected with ROAR, and behavioral data were collected from the target device to facilitate environment simulation. The results obtained by executing prototypes of the RL agent have been aggregated, and the corresponding plots are discussed and compared. These findings suggest that no relation exists between individual actions within an episode and that discounting future rewards does not improve performance in this particular RL problem. Overall, this work demonstrates the feasibility of optimizing ransomware attacks with RL and the effectiveness of the resulting evasion capabilities. The findings derived from the collected results hold in a simulated environment and when the agent is deployed in a real scenario. To our knowledge, this work is the first to investigate the possibilities of supporting malware attacks with RL during the attack phase. Further studies are needed to investigate additional optimizations of the RL model, efficiency improvements to the underlying ransomware implementation, and the feasibility of attacking more powerful devices. |
|
Maximilian Huwyler, Design and Implementation of a Comparison Tool for Selecting an Information Security Risk Assessment Method, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
 
With the increasing relevance of the risk concept in the field of information security, numerous new risk assessment methods have emerged. The selection of a suitable risk assessment method can prove itself to be a first obstacle for organizations that do not have the financial resources to employ consulting firms that assist with the risk assessment process. To address this challenge, comparison methods and tools have been developed in academia and the private sector. This thesis provides a comprehensive review of these methods and tools. An improved comparison method is designed based on this review and an in-depth analysis of several common information risk assessment methods. This method is then used to evaluate nine information security risk assessment methods. A navigable prototype for an information security risk assessment knowledge base has been designed and implemented, with the aim of facilitating comparison between methods and helping users select the most suitable assessment method. The improved comparison method is shown to be superior to predecessors by demonstrating that crucial criteria are adopted and novel criteria improve the selection process. Finally, a use case illustrates the efficiency of the prototype. |
|
Chaoran Xu, Will News Sentiment Save Dollar Carry From Crash?, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)

We aim to enhance the performance of the standard dollar carry by harnessing news sentiment. Our study
focuses on determining the impact of news sentiment on the average spot returns of the G10 currency
basket against the USD at the monthly level. The empirical analyses reveal the existence of a predictive relationship between the two variables. Additionally, we observe that the effect of USD news sentiment varies across different quantiles of the average spot returns. Given that, we propose two news sentiment enhanced dollar carry strategies. The first strategy exploits the result of our initial findings, while the second one further leverages information from both of our research insights. The predictability manifests itself in the form of higher Sharpe ratios of our two augmented dollar carry strategies over both the whole sample period (February 2000 to March 2022) and the out-of-sample period (January 2014 to March 2022) than that of the standard dollar carry when transaction costs are disregarded. Notably, during the out-ofsample period, the second strategy generates a Sharpe ratio of 0.48 and the first strategy 0.43, compared to the benchmark’s -0.22. Despite the fact that transaction costs can eat up a large part of the profits, our
findings suggest that news sentiment still has the ability to improve the dollar carry strategy by achieving excess returns. This is evident in the out-of-sample period, where news sentiment based strategies continue to outperform the benchmark.
|
|
Lukas Grässle, Exploratory Data Analysis of People also asked Questions and Answers on Google in the Domain of Complementary and Alternative Medicine, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
 
This thesis conducts an explorative data analysis of People also asked (PAA) questions and answers on Google.
The study uses web scraping techniques to collect PAA data for various search terms in the domain of complementary and alternative medicine (CAM).
By performing an algorithmic audit, we show that inside the US, neither the location nor the search history influences the set of questions and answers a user is presented by Google for a given search term.
The collection of PAA data for an array of real-world search terms in the domain of CAM reveals that many of the answers provided by Google are not from independently fact-checked sources, but instead biased websites such as retail businesses or special interest advocacies.
Our results further suggest that the question and answer pairs in PAA might lead to confirmation bias.
|
|
Eduard Cuba, Pattern recognition for particle shower reconstruction; Exploring AI-based methods for calorimetric clustering at the CMS HGCAL, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
 
The number of collisions in the upcoming runs of the Large Hadron Collider at CERN will increase significantly. The increasing amount of data and a higher granularity of the newly developed calorimetric detectors pose a substantial data volume and complexity challenge to the current particle shower reconstruction algorithms. This thesis aims to explore the feasibility of machine-learned models scalable to large data volumes for improving the reconstruction quality of calorimetric particle showers via calorimetric clustering. The goal of calorimetric clustering is to recognize and reconnect fragmented energetic components of particle showers described by three-dimensional spatial structures called tracksters. We show that machine-learned models are viable methods for calorimetric clustering and provide a significant reconstruction performance benefit over classical clustering approaches. Furthermore, we investigate the feasibility of node classification and link prediction problem formulations for training graph neural networks. Experimentally, we show that graph-based models provide a better reconstruction performance, more compact data representation, and better scalability on the tested datasets than feed-forward neural networks. |
|
Tristan Kilian Leitner, Factor Momentum on the example of the MSCI World, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)

|
|
Driton Qazimi, Share Buybacks around the World, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)

|
|
Xinyu Zhu, Efficient in-place iterations in MonetDB, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
 
The enormous growth of stored data continues to challenge our ability to efficiently process and analyze data. Many numerical computations related to state transition based on previous state, e.g., compound interest problems or newton’s method, require a combination of
operations from the relational algebra (project, join, select etc.) and iterations. Moreover, many analytical computations, e.g., Markov chain algorithms or various types of regressions, require a combination of operations from the relational algebra, operations from the linear
algebra, and iterations. Plenty of attempts have been made to solve combinations of those elements, but still improvement needed on time and space consumption.
For example, some solutions focus on fetching data from the database, performing linear algebra operations and iterations, and then putting it back into the database, which lacks the support and optimization of relational algebra. Some solutions focus on linear algebra within the database, but require additional data structures and complicated preset functions, and the correspondence of non-numeric and numerical values is not defined. Moreover, the iteration of some solutions is very space or time consuming due to the operations involving table union and table updates. So, there is still not a very suitable solution that can perfectly combine the three aspects.
Our iterations have ability to cover all three aspects at the same time, require no additional knowledge about Python, R, Hadoop or Spark, more tightly integrate with the classic SQL definition, and handle various types of iterations in more flexible and explicit ways. We describe the definition of our iterations in MonetDB, explain major design (motivated by various
complicated iterations), and discuss key in-place features and future research directions. Finally, we provide applications and experiment results that show the potential of our solutions. |
|
Zehra Turgut, Understanding and predicting the success lifecycle of an influencer, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
 
Although influencer marketing has been experiencing tremendous growth, and many firms have been trying to find the right influencers for their marketing campaigns, there has been little research on identifying the timing of the high-impact work or analyzing the hot streak periods of influencers on social media. My thesis is among the first works in this area on the TikTok platform where I applied some methods used in previous literature. All the analyses were made using the video-level popularity metrics of TikTok: “number of likes”, “number of shares”,
“number of plays”, and “number of comments”. In addition, unlike other studies, I created the visualization of the hot streak durations of TikTok authors to analyze information such as the start, and end time of hot streaks, or the length of hot streaks for each author. All plots for the analyses were built with bokeh- a Python library for interactive data visualizations. In conclusion, with the dataset in my thesis study, first I found that the timing of the most popular video is random in TikTok users’ lifecycles. Second, I discovered that the timing of the biggest hit and the second hit are close to each other, so TikTok authors may experience average success close to their most popular videos. Third, I detected a pattern indicating that TikTok authors use more diverse hashtags during hot streak periods than before them. Lastly, I observed that the relative hot streak length -success duration- of an author is usually between 12% and 50%. As a result, marketers can use these observations in my thesis to identify successful influencers on the TikTok platform. Finally, the formulas and visualization methods used in my thesis can be applied to a larger TikTok dataset or other datasets from other social media platforms such as Instagram, or YouTube. |
|
Saskia Senn, Testing Momentum Strategies using Python, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)

The aim of this thesis is to develop an automated correction tool using the
Python programming language to efficiently correct the Involving Activity 3 in the
course Asset Management: Investments. The exercise requires students to create
two momentum strategies based on historical stock prices of 18 stocks using varying
look-back and holding periods. The tool is designed to be highly flexible in terms
of input data, loock-back, and holding periods, enabling the momentum strategies
to be effectively tested and compared to a buy-and-hold strategy. The tool offers a
powerful approach for correcting the Involving Activity 3 leading to faster processing
times and minimized errors compared to manual correction methods. |
|
Jonas Hefti, Bank Funding Costs and the new reference rate SARON, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)

During the global financial crisis, a detachment of the LIBOR from banks’ borrowing costs led to investigations, revealing severe misreporting of quotes in the fixing methodology. Subsequently, the LIBOR was discontinued and replaced by the SARON in Switzerland. By estimating bank level average borrowing costs of major Swiss banks and applying a
Difference-in-Differences model, this thesis analyzes their evolution and drivers. Monetary policy, market risk and the term structure of liabilities significantly influence borrowing costs, while no advantage for too-big-to-fail banks is identified. In addition, SARON is more correlated to the estimated borrowing costs than LIBOR, indicating a better fit. |
|
Jan Toczynski, Essays in Empirical Finance, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Dissertation)

|
|
Nikola Gajic, Political CSR und moralische Legitimität: Eine Fallstudie am Beispiel des IOC und der Olympischen Spiele in China, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)

|
|
Jan Bieser, Ralph Hintemann, Lorenz Hilty, Severin Beucker, A review of assessments of the greenhouse gas footprint and abatement potential of information and communication technology, Environmental Impact Assessment Review, Vol. 99 (107033), 2023. (Journal Article)
 
Various studies have assessed the GHG footprint of the ICT sector (ICT end-user devices, data centers, telecommunication networks) and the potential of ICT use cases (e.g. smart homes, ride sharing) to avoid GHG emissions in other sectors (e.g buildings, transport). We systematically compare relevant studies from the last ten years and discuss the robustness of results in view of the methods used. The results show that the ICT sector causes between 1.5% and 4% of global GHG emissions, a major share of which is due to the production of ICT end-user devices. Estimating GHG impacts of device production is the main source of uncertainty. Results of studies on ICT's GHG abatement potential are less robust, in particular due to uncertainty with regard to use case impacts in a real-life setting, types and sizes of economy-wide rebound effects. Thus the existing studies do not provide a reliable basis for estimating the actually realized GHG abatements. To improve the assessment results and provide a more reliable basis for deriving GHG reduction measures future research should empirically investigate which solution design and accompanying policies are suitable to exploit GHG reduction potentials in real-life. Results of these studies would also increase the robustness of assessments of GHG abatement potentials. |
|
Giulio Cornelli, Jon Frost, Leonardo Gambacorta, Raghavendra Rau, Robert Wardrop, Tania Ziegler, Fintech and big tech credit: drivers of the growth of digital lending, Journal of Banking and Finance, Vol. 148, 2023. (Journal Article)

Fintech and big tech companies are making rapid inroads into credit markets. We hand construct a global database of fintech and big tech lending volumes for 79 countries over 2013-2018. Using a panel regression analysis, we find these new forms of digital lending are larger in countries with higher GDP per capita (albeit at a declining rate), where banking sector mark-ups are higher, and where banking regulation is less stringent. We also find that these alternative forms of credit are more developed where the ease of doing business is greater, investor protection disclosure and the efficiency of the judicial system are more advanced, and where bond and equity markets are more developed. Overall, fintech and big tech credit seem to complement other forms of credit, rather than substitute for them. |
|
Robert Göx, Beatrice Michaeli, Private Predecision Information and the Pay-Performance Relation, The accounting review, Vol. 98 (2), 2023. (Journal Article)
 
We study how the precision of managers' private post-contract predecision information affects the pay-performance relation. Endogenizing the information environment, we find that firms may optimally tie executive pay closer to firm performance as agency problems become more pronounced. Specifically, varying parameters measuring the severity of the agency problem, we identify parameter regions where firms with more pronounced agency problems optimally combine uninformative signals with a higher incentive rate than firms with less pronounced agency problems that optimally choose a perfect signal. We find this relation for various measures of the agency conflict such as the incongruency of the performance measure, its susceptibility to manipulation, or the agent's degree of risk aversion. Because the pay-performance sensitivity (PPS) is frequently used for measuring the efficiency of real world compensation arrangements, our results provide relevant insights for empirical research studying the determinants of the relation between executive pay and firm performance. |
|
Michelle Yik, Chiel Mues, Irene N L Sze, Peter Kuppens, Francis Tuerlinckx, Kim De Roover, Felity H C Kwok, Shalom H Schwartz, Jan Cieciuch, Willibald Ruch, Alexander Georg Stahlmann, On the relationship between valence and arousal in samples across the globe, Emotion, Vol. 23 (2), 2023. (Journal Article)
 
Affect is involved in many psychological phenomena, but a descriptive structure, long sought, has been elusive. Valence and arousal are fundamental, and a key question–the focus of the present study–is the relationship between them. Valence is sometimes thought to be independent of arousal, but, in some studies (representing too few societies in the world) arousal was found to vary with valence. One common finding is that arousal is lowest at neutral valence and increases with both positive and negative valence: a symmetric V-shaped relationship. In the study reported here of self-reported affect during a remembered moment (N = 8,590), we tested the valence-arousal relationship in 33 societies with 25 different languages. The two most common hypotheses in the literature–independence and a symmetric V-shaped relationship–were not supported. With data of all samples pooled, arousal increased with positive but not negative valence. Valence accounted for between 5% (Finland) and 43% (China Beijing) of the variance in arousal. Although there is evidence for a structural relationship between the two, there is also a large amount of variability in this relation. |
|