At What Price? Exploring the Potential and Challenges of Differentially Private Machine Learning for Healthcare

2023 | HICSS | Citations: 1

Authors: Aslan, Aycan; Matschak, Tizian; Greve, Maike; Trang, Simon; Kolbe, Lutz

Abstract: The increased generation of data has become one of the main drivers of technolog ... Expand

Abstract: The increased generation of data has become one of the main drivers of technological innovation in healthcare. This applies in particular to the adoption of Machine Learning models that are used to generate value from the growing available healthcare data. However, the increased processing of sensitive healthcare data comes with challenges in terms of data privacy. Differential privacy, the method of adding randomness to the data to increase privacy, has gained popularity in the last few years as a possible solution. However, while the addition of randomness increases privacy, it also reduces overall model performance, generating a privacy-utility trade-off. Examining this trade-off, we contribute to the literature by providing an empirical paper that experimentally evaluates two prominent and innovative methods of differentially private Machine Learning on medical image and text data to deepen the understanding of the existing potential and challenges of such methods for the healthcare domain. Collapse

Topics: privacy differential privacy healthcare data knowledge base data protection

Methods: experiment computational algorithm machine learning blood pressure PyTorch

Building Digital Trust to Protect Whistleblowers - A blockchain-based Reporting Channel

2023 | HICSS | Citations: 0

Authors: Asprion, Petra; Grieder, Hermann; Grimmberg, Frank; Moriggl, Pascal

Abstract: Organizations today need internal reporting channels to report illegal/unethical ... Expand

Abstract: Organizations today need internal reporting channels to report illegal/unethical misconduct. For this purpose, organizations set up one or more - often digital - internal reporting channels. Persons/Employees who want to report misconduct, so-called whistleblowers, expose themselves to reprisals and therefore need trustworthy reporting channels which ensure ´Digital Trust´. Blockchain, a technology that overcomes the need for trust due to its properties of immutability and integrity of data, could be promising as underlying technology for a digital reporting channel which is recognized as trustworthy. In our research, we explored multiple perspectives relevant to a trustworthy digital reporting system. Applying design science research, we evaluated the current state of the art of (digital) reporting channels and developed a prototypical blockchain-based reporting solution called “Integrity@Inside”. The prototype is being iteratively demonstrated and pre-evaluated. Collapse

Topics: blockchain electronic health privacy IT security usability

Methods: design artifact qualitative interview design process design science expert panel

Privacy Regulation and Its Unintended Consequence on Consumption Behaviors: Evidence From CCPA

2023 | International Conference on Information Systems | Citations: 0

Authors: Bae, Donghwa; Mayya, Raveesh; Nian, Tingting

Abstract: This study explores the unintended consequences of data protection regulations ... Expand

Abstract: This study explores the unintended consequences of data protection regulations on consumer behavior. Specifically, we examine the California Consumer Privacy Act, which restricts companies from collecting Californians' personal information. Privacy regulations may limit firms' ability to suggest products aligned with consumers' taste predicted from data, potentially influencing subsequent consumer behavior. These regulations especially pose a challenge to digital platforms, as their success hinges on seamless data flow between firms and consumers. Using a difference-in-differences approach with transaction data, we find that post-CCPA, Californians reduce purchase by 4.1%, increase returns by 2.9%. Moreover, we find that Californians spend more time online and visit more webpages, potentially indicating increased search efforts. Mechanism analysis suggests that firms under CCPA proactively alter their data collection strategy to reduce the liability. These results reveal the complex interplay between privacy regulation and consumer behavior, highlighting the need for a nuanced understanding of the trade-offs between privacy protection and economic outcomes. Collapse

Topics: information privacy law legal context consumer behavior advertising management website

Methods: experimental group longitudinal research natural experiment archival research difference in differences

Artificial Intelligence as a Service: Trade-Offs Impacting Service Design and Selection

2023 | International Conference on Information Systems | Citations: 0

Authors: Brecker, Kathrin; Lins, Sebastian; Trenz, Manuel; Sunyaev, Ali

Abstract: AI as a Service (AIaaS) is a promising path to leverage AI capabilities from th ... Expand

Abstract: AI as a Service (AIaaS) is a promising path to leverage AI capabilities from the cloud. However, there is no one-size-fits-all service, but heterogenous service options since interdependent AIaaS characteristics require trade-offs. We lack knowledge on these tradeoffs and how they result from conflicting characteristics. Therefore, we interviewed 39 AIaaS providers, customers, and consultants to provide rich descriptions of interdependent characteristics and uncover resulting trade-offs and their consequences. This study contributes to a better understanding of the inner functioning and interplay of AIaaS characteristics and discusses how this complex nature of service offerings impacts providers' design and customers' selection decisions. Collapse

Topics: artificial intelligence cloud computing ease of use data protection economies of scale

Methods: qualitative interview design artifact constant comparative analysis qualitative coding triangulation

Theories: SERVQUAL core competency theory

Excuse Me, Something Is Unfair! - Implications of Perceived Fairness of Service Robots

2023 | European Conference On Information Systems | Citations: 0

Authors: Büttner, Sebastian; Sourkounis, Cora Maria; Gutzmann, Jan; Prilla, Michael

Abstract: Fairness is an important aspect for individuals and teams. This also applies to ... Expand

Abstract: Fairness is an important aspect for individuals and teams. This also applies to human-robot interaction (HRI). Especially if intelligent robots provide services to multiple humans, humans may feel treated unfairly by robots. Most work in this area deals with the aspects of fair algorithms, task allocation, and decision support. This work focuses on a different, yet little-explored perspective, which looks at fairness in HRI from a human-centered perspective in human-robot teams. We present an experiment in which a service robot was responsible for distributing resources among competing team members -in one condition with an efficient (but rather unfair) distribution algorithm and in another condition with an algorithm that was less efficient but could be considered fair. We investigated how the different strategies of distribution influence the perceived fairness and how this perceived fairness influenced the perception of the robot as such. Our study shows that humans might perceive technically efficient algorithms executed by a robot as unfair, especially if humans personally experience negative consequences. Interestingly, this perceived unfairness had a negative impact on human perception of the robot as such, which should be considered in the design of future robots. Collapse

Topics: robotic user acceptance user interface artificial intelligence data quality

Methods: experiment nonparametric test computational algorithm Mann Whitney U test survey

Promise not fulfilled: FinTech, data privacy, and the GDPR

2023 | Electronic Markets | Citations: 0

Authors: Dorfleitner, Gregor; Hornuf, Lars; Kreppmeier, Julia

Abstract: This article analyzes how the General Data Protection Regulation (GDPR) has affe ... Expand

Abstract: This article analyzes how the General Data Protection Regulation (GDPR) has affected the privacy practices of FinTech firms. We study the content of 276 privacy statements respectively before and after the GDPR became binding. Using text analysis methods, we find that the readability of the privacy statements has decreased. The texts of privacy statements have become longer and use more standardized language, resulting in worse user comprehension. This calls into question whether the GDPR has achieved its original goal—the protection of natural persons regarding the transparent processing of personal data. We also link the content of the privacy statements to FinTech-specific determinants. Before the GDPR became binding, more external investors and a higher legal capital were related to a higher quantity of data processed and more transparency, but not thereafter. Finally, we document mimicking behavior among FinTech industry peers with regard to the data processed and transparency. Collapse

Topics: legal context General Data Protection Regulation privacy electronic finance website

Methods: parametric test paired t-test descriptive statistic Student's t-test qualitative content analysis

Theories: privacy calculus theory

z-Commerce: Designing a Data-Minimizing One-Click Checkout Solution

2023 | DESRIST | Citations: 0

Authors: Ermolaev, Egor; Abellán Álvarez, Iván; Sedlmeir, Johannes; Fridgen, Gilbert

Abstract: E-commerce has grown rapidly over the past years, with prevailing e-commerce pla ... Expand

Abstract: E-commerce has grown rapidly over the past years, with prevailing e-commerce platforms aggregating large amounts of customer data. This practice has several undesirable side effects, such as facilitating profiling that may lead to price discrimination and data feedback loops that can hamper competition. Moreover, data hoarding carries security risks through data breaches and undermines customers’ privacy expectations. On the other hand, convenience aspects and compliance regulation demand the processing and storage of user-related data. To address this tension field, we aim to conceptualize and iteratively refine a data-minimizinig e-commerce platform. Following a design science research approach, we identify design objectives and propose and implement a solution in which stakeholders receive only customer data that is indispensable for their part of the process. Our solution leverages digital identity wallets and general-purpose zero-knowledge proofs (zk-SNARKs). We aim to perform a criteria-based evaluation to assess our artifact’s feasibility and fitness from an interdisciplinary perspective. With our results, we hope to illustrate that combining state-of-the-art cryptographic techniques and an emerging digital identity paradigm allows reaching the user experience of incumbent e-commerce platforms while mitigating the undesirable socio-economic side effects of avoidable data disclosure. Collapse

Topics: electronic commerce privacy user experience open source price discrimination

Methods: qualitative interview design artifact design science literature study business process modeling

Critical Success Factors for AI-driven Smart Energy Services

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Gerlach, Jana; Lier, Sarah; Hoppe, Paul; Breitner, Michael H.

Abstract: Artificial Intelligence (AI) can significantly contribute to decentralizing and ... Expand

Abstract: Artificial Intelligence (AI) can significantly contribute to decentralizing and digitalizing the energy sector and environmental sustainability. Integrating AI-driven smart energy services (SES), such as energy production forecasting, building energy management, and predictive maintenance, remain in an early phase for plant providers or energy utilities. However, the knowledge regarding key factors determining the design of AI-driven SES is limited in the literature. Therefore, we derive critical success factors (CSFs) for the design of AI-driven SES in a design science research (DSR) approach in connection with the design thinking process. We identified ten CSFs and 31 CSF categories by iteratively combining the knowledge of interviewed AI business experts, scientific literature, and results of AI programming projects with students. Based on this, we developed a further research agenda containing six research demands and direct further research questions. KeywordsArtificial intelligence, energy sector, critical success factors, design thinking, design science research. Research Needs and MotivationAI solutions in the energy sector can be deployed for various tasks, such as energy generation forecasting, demand side management, building energy management, weather forecasting, predictive maintenance, plant and storage management, and energy price forecasting (Li et al. 2022). A forecast for the year 2025 predicts that the AI software market will generate annual revenue of 126 billion US dollars (Omdia 2020). Reasons for the increasing integration are the development of technologies for the collection and storage of big data and the constantly evolving computing power (Haenlein and Kaplan 2019). According to Nishant et al. (2020) AI systems in the energy sector contribute threefold: to task automation, gaining insights from data, e.g., documents, videos, and e-mails, and solving complex problems through computing capabilities. Automation tasks include the automated usage of drones for inspection and safety purposes. Gaining insights from data involves image analysis to provide predictive maintenance for power lines or energy production forecasting for energy planning. Solving complex problems includes planning efficient and multiple usages of battery storage (Nishant et al. 2020;Quest et al. 2022). Therefore, AI solutions, here AIdriven SES, can significantly impact energy efficiency and contribute to environmental sustainability, decarbonization, and decentralization of the energy sector (Antonopoulos et al. 2020;Nishant et al. 2020). Environmental sustainability, one of the three dimensions of sustainable development, concerns climate change and the measures required to quantify and reduce its impacts. Sustainability must be understood as consuming natural resources only so that future generations are not exposed to natural resource depletion (Purvis et al. 2019). Current literature on AI-driven SES addresses AI and Machine Learning (ML) models (Li et al. 2022), application areas and business models (Antonopoulos et al. 2020;Li et al. 2022;Quest et al. 2022), and advantages and disadvantages (Ahmad et al. 2021;Benbya et al. 2020). However, knowledge CSFs for AI-driven Smart Energy Services Collapse

Topics: artificial intelligence design thinking critical success factor user interface explainable artificial intelligence

Methods: design methodology qualitative interview literature study personal interview computational algorithm

Law, Economics, and Privacy: Implications of Government Policies on Website and Third-Party Information Sharing

2023 | Information Systems Research | Citations: 0

Authors: Gopal, Ram D.; Hidaji, Hooman; Kutlu, Sule Nur; Patterson, Raymond A.; Yaraghi, Niam

Abstract: Widespread abuse of internet users’ privacy online has prompted user advocacy gr ... Expand

Abstract: Widespread abuse of internet users’ privacy online has prompted user advocacy groups to implore governments to intervene and protect consumer rights. To study such interventions’ effects, we examine data-protection policies that policy makers and governments can enforce on websites, including consent-based user information sharing and subsidizing competing websites. We use a stylized analytical model to examine such policies’ impact on the decisions and outcomes of websites, users, and third-parties. Interestingly, we find that even though a consent-based policy may improve user surplus, in the absence of market entry and exit (static market), it has the unintended consequence of increasing the number of third-parties and, thus, sharing of user information. We also determine that both consent-based and website subsidization policies may reduce competition by driving websites out of the market—to the detriment of user surplus and social welfare. To validate our analytical model’s findings, we empirically investigated the impact of a consent-based policy on third-parties in a natural experiment of the California Consumer Privacy Act. These findings raise significant implications for policy making surrounding online privacy. History: Giri Kumar Tayi, Senior Editor; Nachiketa Sahoo, Associate Editor. Funding: Financial support from the Social Sciences and Humanities Research Council of Canada is gratefully acknowledged. R. D. Gopal gratefully acknowledges support by the Gillmore Centre for Financial Technology at the Warwick Business School. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2022.1178. Collapse

Topics: website information privacy concern data protection privacy legal context

Methods: mathematical model natural experiment experimental group longitudinal research time series analysis

Taking the Person Seriously: Ethically Aware IS Research in the Era of Reinforcement Learning-Based Personalization

2023 | Journal of the Association for Information Systems | Citations: 0

Authors: Greene, Travis; Shmueli, Galit; Ray, Soumya

Abstract: Advances in reinforcement learning and implicit data collection on large-scale ... Expand

Abstract: Advances in reinforcement learning and implicit data collection on large-scale commercial platforms mark the beginning of a new era of personalization aimed at the adaptive control of human user environments. We present five emergent features of this new paradigm of personalization that endanger persons and societies at scale and analyze their potential to reduce personal autonomy, destabilize social and political systems, and facilitate mass surveillance and social control, among other concerns. We argue that current data protection laws, most notably the European Union's General Data Protection Regulation, are limited in their ability to adequately address many of these issues. Nevertheless, we believe that IS researchers are well-situated to engage with and investigate this new era of personalization. We propose three distinct directions for ethically aware reinforcement learning-based personalization research uniquely suited to the strengths of IS researchers across the sociotechnical spectrum. Collapse

Topics: usability personalization legal context General Data Protection Regulation information privacy law

Methods: reinforcement learning computational algorithm simulation language model experiment

Theories: social sciences theory