Michael Vuong, Design and Implementation of a Byzantine Robust Aggregation Mechanism for Decentralized Federated Learning, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
Federated learning has become increasingly more popular due to limitations of the traditional machine learning methods regarding the data privacy. In addition due to technological evolution, the data volume in general has increased by a lot. Mobile devices are capable of storing more and more data.
While traditional machine learning methods struggle to deal with these concerns, federated learning emerged from these problems.
Two main approaches have been mainly used namely Centralized and Decentralized Federated Learning.
The former one has gotten much more attention in comparison with its counterpart and thus possesses many aggregation rules which are resistant to attacks.
The goal of this thesis is to propose a new aggregation rule which is resistant to attacks against the machine learning model for the decentralized setting to fill a gap where the research has no reached yet.
This is done by extending an existing framework fedstellar, for federated learning.
The case studies as part of the evaluation evaluate the algorithm on performance and resource consumption related metrics.
They indicate that the performance of the algorithm depends on the situation. They also show the limitation of the algorithm and possibilities of expanding the algorithm to other applications. |
|
Johann Schwabe, CaVieR: CAscading VIEw tRees, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Maintaining multiple complex queries on large, dynamic datasets in real time poses a major challenge. Thus, this thesis introduces CAscading VIEw tRees (CaVieR), an extension to Factorized Incremental View Maintenance (F-IVM) that addresses this challenge. CaVieR adds a method to F-IVM that joins the view trees of multiple conjunctive queries into a directed acyclic graph (DAG). This can efficiently handle updating and enumerating a set of Cascading Q-Hierarchical Queries. Reducing redundant query maintenance significantly reduces computational workload and can even reduce the theoretical asymptotic
complexity of maintaining Cascading Q-Hierarchical Queries.
The algorithm was tested against F-IVM on synthetic and real-world datasets with different sets of Cascading Q-Hierarchical Queries. In experiments, the two main performance indicators in IVM were measured: update time and enumeration delay. While in most scenarios, a significant improvement in both measurements was observed, it was found that F-IVM, when using batch
updates and ordered input relation streams, can outperform CaVieR.
To verify that this is the only scenario where individually maintaining the view trees is better than joining them, various parameters were tested, and their influence on update time and enumeration delay was recorded. While
parameters like the cardinality of the input relations and the number of free vari- ables significantly influenced the update time and enumeration delay, CaVieR outperformed F-IVM consistently.
Thus this thesis not only presents a new method of optimization to F-IVM that can decrease the asymptotic complexity of the problem, including theoret- ical proofs of correctness and completeness. It also includes an implementation and experiments to estimate its performance impact. |
|
Yuwei Liu, Who wants to “Breeze”? A Cross-Cultural Pilot Study on Intentions to Use Different Versions of a Breathing Training Mobile Game in Germany and the USA, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Background: Gamification and storytelling have been implemented in slow breathing training apps, a proven effective way to reduce stress and improve mental wellbeing, with the goal of keeping users interested and engaged. However, it is widely acknowledged that users’ cultural background and socioeconomic status (SES) affect their perceptions of apps and therefore intentions to use it on a regular basis.
Objective: Based on previous research on user engagement in digital health interventions, cross-cultural human-computer interaction (HCI) and technology acceptance theories, this thesis investigates the intention to use three distinct versions of a slow breathing training app (Stressless©: control group, Breeze©: with gamification, Tragic Kingdom©: with gamification and storytelling) between German and American users.
Methods: Adult US and German nationals were recruited from online crowdsourcing platform Prolific. They were randomly assigned to one of the three condition groups and watched a 1-minute introduction video about the corresponding breathing apps in their preferred language. Afterwards, they reported intention to use in a survey, alongside with other attributes related to technology acceptance that are not evaluated in this thesis. As the dependent variable, aggregated intention to use were summed up based on four survey questions. Independent variables were participants’ nationality and app versions coded as categorical variables.
Results: A total of 325 participants completed the study (153 German participants and 144 from US Americans). The results show that while national culture does not play a significant role in intention to use, the effect of app version is strong. Although not statistically significant, SES differences in intention to use is observed with no moderating effect of national culture.
Conclusion: Even though most hypothesis cannot be rejected; this thesis still provides meaningful guidelines for future studies on cross-cultural and other demographic comparisons on digital health gamification design. |
|
Omar Abo Hamida, MigrantTech: Public Value von digitalen Plattformen zur Erfüllung der Bedürfnisse von Flüchtlingen verstehen, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
Amid the emergence of numerous new digital platforms for refugees in Switzerland developed by NGOs and the public administration, the question of refugee needs is becoming increasingly important. This research paper analyzes the significance of digital platforms in supporting refugees in Switzerland. In doing so, it applies and extends the Public Value concept by Faulkner and Kaufmann. The study is based on 15 interviews with primarily Syrian refugees, which were evaluated using qualitative content analysis. The results offer insights from the refugees' perspective and identify critical aspects in dealing with digital platforms. Building on this, an expanded Public Value concept has been developed. This new concept includes the newly added dimensions of "Information Value", "Community Engagement", and "Role of the Platform". The extension of the model offers a new approach to evaluating and optimizing the use of digital platforms targeted at refugees. |
|
Jonas Gebel, Downtime; Facilitating psychological detachment throughartefact-based reflection, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
Knowledge workers profit immensely from modern technologies and use them for many aspects of their work. But these technologies also come with drawbacks, as people are now more than ever expected to be available at all times via their work devices. This can lead to blurring boundaries between ones work and private life, which in turn can have negative effects on the ability to psychologically detach from work and enjoy non-work time. In this study we introduce the concept of artefact-based reflection, a method through which knowledge workers can reflect on so called work-artefacts, like tabs, files or e-mails, that they worked with throughout their day and "clean up their workplace" at the end of their workday. Based on existing research and this new concept we developed Downtime, an application which aims at helping knowledge workers in facilitating psychological detachment through artefact-based reflection. We then conducted a user study over two weeks to evaluate the effects of our application. Our findings suggest that knowledge workers can increase their detachment from work and create mental boundaries between their work and non-work lives through reflecting upon the work-artefacts they used that day, especially when they were not actively seeking detachment from their work beforehand. Further research is necessary to evaluate the long-term effects of artefact-based reflection on a broader range of knowledge workers. |
|
Jason Browne, Assessing the Positive and Negative Impacts of Privately-Owned Digital Platforms on Public Value in Switzerland, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
The growth of privately held digital platforms has had a significant impact on socioeconomic development and technical innovation. While most of these platforms are primarily focused on generating business value, there is a subset that operates as public service platforms, providing citizens with access to public services. However, it is essential to determine whether these privately held public service platforms contribute to or detract from public value. This research aims to address two primary research questions within the Swiss context. Firstly, it investigates how Swiss-based privately-owned digital platforms contribute to and destroy public value creation. Secondly, it explores citizens' expectations regarding public value creation through Swiss-based privately-owned digital platforms. A multiple case study approach was employed, analyzing three platforms: Coople, Homegate, and Ricardo. By employing the Public Value Scorecard framework, the analysis focused on assessing various dimensions of public value. The research involved conducting interviews and conducting a comprehensive analysis of grey literature, including Google Play reviews and newspaper articles sourced from the Swissdox database. The findings suggest that users highly value the efficiency aspect and the resulting transparency offered by these platforms. However, concerns arise regarding the quality of service, the level of personalization, as well as the platforms' responsibility and accountability. |
|
Ben Domenic James Murphy, Machine Learning Approach to Polkadot’s Validator Selection Algorithm, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Polkadot’s validator selection process employs an iterative algorithm, which is dependent on the size of the staking system. As Polkadot’s staking network is growing, I propose a machine learning alternative approach to the current implementation, that is more independent of scale. The algorithm, the sequential Phragmén, aims to reduce a graph of nominator-validator edges to a subset of validators, the active set, and distribute the stake backing them, as evenly as possible. The goal of this thesis is to produce superior results, consequently improving the overall security or to provide solutions of equal quality in faster time.
In order to achieve the goal, a pipeline is setup, that gathers data and transforms it such that it is suitable for machine learning models. Predictions are made, which are adjusted to fit the requirements set by Polkadot. The adjusted results are scored and ultimately compared to the solutions discovered by sequential Phragmén.
An analysis of the training data reveals, that the active set remains highly static, with only 10 validators on average changing from era to era. This lack of diversity raised concerns regarding potential attack vectors for adversaries. Furthermore, it was observed that many nominators are acting inefficiently. Many of them do not execute their right to nominate up to 16 validators, which would maximize their chance of having a validator included in the active set. Additionally, many of them include validators, which are not eligible targets. This occurs since nominators frequently ignore their duty to actively tend to their validator preferences. They set them once and do not update them.
Eligible validators become inactive (intentionally or unintentionally) and consequently remain as part of the nominators preferences.
The prediction task was split up into three models: The first model predicts the next active set, the second model predicts the sum of stake each validator receives and the third predicts the individual stake distribution. The results show, that the first two models are trained well and produce satisfactory results. However, the learning curves of the third model reveal a bias, which make the predictions suboptimal. The source of the bias is likely the substantial changes in target values introduced by a slight shift of active set.
We conclude that it is unlikely to outperform the sequential Phragmén using a supervised approach under the described conditions. Therefore, we recommend exploring an unsupervised approach for further research. Furthermore, we recommend the development of a tool for nominators, that could increase the convenience and the security of the overall staking system as a consequence. |
|
Florian Rüegsegger, Inter-Chain Data Collection Pipeline For The Polkadot Ecosystem, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
This thesis aims to increase the capabilities of the Polkadot Data Preprocessing Pipeline of the Blockchain Observatory (BCO), a project of the Blockchain and Distributed Ledger Technologies Group (BDLT) at University of Zurich (UZH). This pipeline currently collects data of the Polkadot Relay chain. With the recent launch of Parachains, the Polkadot ecosystem expanded considerably.
The aim of this thesis is to expand the pipeline to two Parachains, namely Moonbeam, a Ethereum Virtual Machine (EVM) compatible Parachain, and Interlay, a bridge to Bitcoin (BTC). Furthermore, Cross-Consensus Message Transfer (XCM) between the chains should also be handled.
The new Pipelines consist of an archive node, a producer module and a preprocessing module per chain. The node provides raw data, the producer stores the raw data, while making sure the data is valid and checking and correcting the database integrity. The preprocessor finally preprocesses the raw data received, making use of the node for storage queries and web3 interactions in the case of Moonbeam. The data collected focuses on historical balance and transfer data, staking and reward data and data concerning the specific Parachains, such as ERC-20 Tokens on Moonbeam and vaults on Interlay.
A part of the thesis was dedicated to the optimization of the pipeline to increase the speed of data collection by restructuring the preprocessor to only use batched queries per block processed. The memory footprint was reduced by removing redundant data.
Finally, some queries and visualization are showcased to highlight interesting aspects of the data and to demonstrate the capabilities of the preprocessor, as well as providing examples. |
|
Laura Vogt, Design of a Corporate Identity Training for Organisations supported by a Pedagogical Conversational Agent, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
Incorporating Pedagogical Conversational Agents (PCAs) into learning environments has shown promising benefits for learning. However, most of the research has been performed in the field of academia. Building on a previous paper, this study focuses on the application of PCAs for organisational workplace learning. Having a strong Corporate Identity (CI) has become a competitive advantage for companies. In sectors, like public administrations that have a distinct service side, training staff on CI can be beneficial for the organisation. This thesis is part of a bigger research project that designed and implemented a CI Training for two public administrations in Southern Germany. Using Action Design Research, this thesis focused on designing a learning platform and learning videos that aimed to train staff on external communication, based on existing theories about multimedia learning and practice-inspired research. The main role of this thesis in the project was to design the usability of the learning platform, the experience of the learners, as well as the learning videos. So far, no uniform guidelines for the design of learning platforms that include a Pedagogical Agent (PA) could be found. The aim of this thesis was therefore to investigate the interaction of the agent, the platform, and the learner, thus contributing towards answering the question how a successful workplace training environment, that is supported by a PCA, can be designed. The results showed that incorporating a PCA into the learning environment increased the overall usability of the platform, especially the perceived control that the learners have over the interactions with the platform. The agent initially motivated the participants, however, this motivation declined as the agent did not perform to their expectations. No effect of the PCA-supported learning treatments on self-efficacy or self-determination could be found, in comparison to traditional e-learning without a PCA. Based on the results and on the qualitative feedback from the participants, design principles for PCA-supported learning environments were formulated. The data and results of this thesis can be used for further iterations of the overarching research project. Simultaneously, it can serve as a source of information for the design of other PCA-supported learning environments. |
|
Cédric Merz, Self-Sovereign Identities for Refugees: The Case of the Swiss Canton of Zurich, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
The Ukrainian refugee crisis beginning in 2022 revealed challenges for both refugees and organisations in the Swiss asylum process. While refugees are faced with time-consuming and cumbersome administrative tasks and repetitive forms, the many involved authorities and organisations are overwhelmed with slow and paper-based processes, redundant work, and wrong data. In this thesis, I suggest a digital ID stored in a smartphone-based “wallet” applying the concept and technology of Self-Sovereign Identity (SSI) to mitigate these issues. Following a design science research approach, I iteratively developed a prototype and evaluated it with a total of 14 refugees and five experts from different organisations. The results show that a digital ID would ease the lives of refugees and possibly empower them. Concerning organisations, the potential for improved interoperability is limited, but experts agree that efficiency in processes would likely be increased. Ultimately, this thesis derives learnings from the results on how to design an SSI-based ID for refugees and discusses its potential. |
|
Gabriele Brunini, Deep Learning with Temporal Context for Sleep Stage Classification, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
Detecting and solving sleep disorders can significantly impact society and the economy in general. The polysomnogram is the gold standard exam for diagnosing sleep disorders. Manually annotating the patient's sleep has limitations, including its time-consuming and tedious nature, lack of reliability, sensitivity to the setup of different clinics, and motion noise. This work tests the ability of neural network models to be faster and more reliable than manual scoring by incorporating temporal information in the training setting and changing the model architecture. The study concentrates on algorithms that are robust to the setup of different clinics and fair to diverse populations, using an intelligent combination of the most used datasets in experimental settings: the Sleep-EDF and the MASS datasets. We first analyze the ability of the automated classifier to handle data from different sleep centers and patient groups by experimentally testing loss functions and other crucial model parameters across datasets. Then, we incorporate temporal context in the data samples by concatenating previous sleep epochs to the current sample. We show that our model trained on longer temporal context performs equally to many of the analyzed manual sleep stage scoring conducted by expert technicians and is superior to some state-of-the-art models we analyzed. |
|
Joe Müller, VisKnowsBest: A Web Catalogue of Visualization Guidelines and Best Practices, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
Visualization guidelines are one of the core elements of the visualization field. Guidelines pose an essential role for practitioners, researchers and students alike and therefore they should not just be accepted as they are proposed, but discussed, evolved and verified as thoroughly as possible. Currently, only a small amount of the proposed visualization guidelines go through this in-depth process, with the majority of them being the more prominent guidelines, such as the Data-Ink-Ratio or the Chart-Junk debate. While there are tools showcasing categorizations of visualization guidelines and forums for discussing them, there is no tool that acts as an accessible and easily navigable central source of knowledge for visualization guidelines. In the scope of this thesis, a tool is developed that provides guidance and context on visualization guidelines by providing additional information such as taxonomies and related scientific resources. To showcase the functionality of the tool, additional data required to provide guidance on visualization guidelines will be collected. The collected data is added to an existing collection of visualization guideline related data. The complete data will then be displayed on the VisKnowsBest tool to showcase a tool with the potential of acting as a central repository for visualization guidelines. |
|
Yunhao Chen , An explanation for the price disparity in the segmented market: evidence from dual-listed firms in the Chinese and US stock market, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
This paper investigates the relationship between stock liquidity and the corresponding ADR shares discount using a sample of cross-listed firms in both the A shares market in China and the ADR market in the USA. The liquidity hypothesis is examined by introducing the market depth variables. The result of this study indicates that a smaller difference in stock liquidity between A shares and ADR is related to a lower corresponding discount in the ADR market. Such an effect is validated by the subperiod check. Overall, this study highlights that market liquidity of cross-listed stocks explains a proportion of the variation in price disparity that long existed in the ADR market. Meanwhile, a stock-specific factor for the price disparity is also proposed in this paper. |
|
ZHOU YE, The effect of firm-specific exchange rate on research and development: Evidence from China, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
|
|
Jérôme Gretener, Economic and Financial Drivers of Forest Cover Change, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
|
|
Jennifer Li, Factor Models during financially turbulent Times, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
This bachelor’s thesis presents an examination of factors, such as the factors introduced by Fama
and French (2014), as well as Carhart (1997). Additional factors are built using financial ratios.
The research is done on US stocks from 1990 to 2021. The factor’s ability to explain asset returns
is observed by doing two simple linear regressions. To visualize interrelations, a correlation matrix
is analyzed. From the factors that are already established in existing literature, the excess market
return, profitability, investment and momentum factors are good at explaining returns. Besides,
factors built using one of these ratios have a significant influence: Price to earnings, free cash flow to
operating cash flow, or interest coverage. Further, a factor model is constructed based on financially
turbulent times. That is, taking the factors that had the best performance during drawdowns.
When conducting a multi-linear regression and a test by Gibbons et al. (1989), it appears that this
multi-factor model does not capture the expected returns accurately, therefore it is not using its full
potential efficiency. This shows that when constructing a new factor model, the criteria for the factor
choice should be extended. |
|
Witold Rozek, Government as a platform: an automated media analysis of crisis-related publications. The case of the Russian invasion in Ukraine., University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
Media analysis reflects the most important facts about public opinion and the actors involved in the most current topics. It is beneficial for the government and the public administration to identify the information gaps in the public media to intervene and assist in specific areas concerning the reception and acclimatization process of Ukrainian refugees in Switzerland. This study aims to explore the potential of combining the three Natural Language Processing (NLP) techniques, Named Entity Recognition (NER), Sentiment Analysis (SA), and Topic Modeling (TM), with Machine Learning (ML) models to facilitate decision-making by the authorities.
The data used for this study consist of German- and English-speaking articles retrieved from Swiss news media related to the Russian-Ukrainian war. The data includes articles between February 2022 and January 2023. The research approach is split into three main parts, data exploration,
the modeling phase, and the evaluation of the models. During data exploration, the data was preprocessed and filtered in relation to Ukrainian refugees. In the modeling phase, the used ML models were introduced, fine-tuned, and applied to the data, leading to the final results. Using the three abovementioned NLP techniques, the most common topics, the article's sentiment over time, and the most common entities in the data could be identified. SA reveals a change of 5% from positive to negative articles regarding the total sum. TM presents the most common topics related to the Ukrainian refugee crisis in Switzerland. NER uncovers the most affected actors, locations, and organizations impacted by the crisis. In the evaluation phase, the model's performances were analyzed, which resulted in a remarkable accuracy score of 96.5% for the NER model, an average accuracy score of 62.5% for the SA model, and a coherence score of 0.65 for BERTopic, the TM model.
To conclude, the research shows the potential of using ML-based NLP techniques on news media data to extract beneficial facts from a huge amount of data regarding the case of the Russian-Ukrainian war. |
|
Shivam Gupta, What Determines Real Estate Prices? Evidence from House-Level Data for Switzerland, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Bachelor's Thesis)
This bachelor thesis investigates the factors determining real estate prices in Switzerland
by focusing on different regions, key characteristics of individual homes, and various
economic factors.
The study explores the impact of these components on the sales price by using linear
regression and other statistical methods. The “Comparis” database was used to collect data
such as geographical variables and property features of single-family houses. The results
highlight the effect of these components on housing prices. They can even explain price
development and volatility over the past few years. In conclusion, this study gives valuable
insights into the Swiss real estate market by considering regional, property-specific, and
economic aspects. |
|
Zhixi Wei, Has the Last-resort Small Business Lending been Screened Enough: Evidence from SBA Data, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
This paper examines the impact of the government’s partial guarantee loan provision (SBA 7(a)
program) on small business lending during financial constraint periods. Our goal is to determine
if access to loan securitization reduces banks’ incentives to screen borrowers, potentially leading to
weakened screening standards. Our regression model and matching procedure support the idea that
banks with high originate-to-distribute (OTD) ratios have sufficiently screened risky borrowers, which
is supported by the evidence that high OTD banks have a wider loan pricing residual distribution.
After looking into capital structure, we further confirm that banks are using SBA loans and the
responsive secondary market to save regulatory capital, rather than diluting screening standards.
This research provides insights into understanding government-guaranteed lending programs, the
role of soft information in lending decisions, and the effects of loan sales on loan performance.
Keywords: Originate-to-distribute, Small business lending, Financial crisis, Screening incentive,
Government-guaranteed lending |
|
Siyang Tian, Real Effects of Supervisory Enforcement Actions on Bank Performance: Evidence from China, University of Zurich, Faculty of Business, Economics and Informatics, 2023. (Master's Thesis)
This thesis aims to provide insights into effects of supervisory enforcement actions (EAs) on
various aspects of bank performance. To achieve this, a comprehensive dataset encompassing
bank performance metrics and regulatory enforcement actions in China from the period 2002
to 2022 is utilized for quantitative analyses. The research begins with a two-way fixed effect
Ordinary Least Squares (OLS) model to identify the effects on key variables related to bank
performance. Subsequently, the study employs the event study methodology to compare the
performance of banks before and after the implementation of EAs. Baseline results reveal that
EAs have notable effects on bank behavior. Specifically, EAs are found to (1)limit banks’ asset
expansion, (2)decrease the profitability of punished banks and (3)improve capital adequacy
of affected banks. Besides, banks subject to EAs exhibit worse loan quality and structure
compared to unaffected banks. These effects are amplified in cases where banks are subject to
severe EAs. Event study findings suggest that the effects of EAs usually lasts for on more than
two years. Moreover, the analysis captures some pre-treatment effects, providing additional
insights into the anticipation and response of banks to impending regulatory actions. |
|