004 Datenverarbeitung; Informatik
Refine
Document Type
- Article (20) (remove)
Language
- English (20) (remove)
Has Fulltext
- yes (20)
Is part of the Bibliography
- no (20)
Keywords
- Machine learning (2)
- machine learning (2)
- (mobile) Internet (1)
- AI fairness (1)
- Adoption (1)
- Algorithmic fairness (1)
- App (1)
- Artificial intelligence (1)
- Automated Feedback (1)
- COVID-19 news (1)
Institute
- Wirtschaftswissenschaften (20) (remove)
Optimal investment decisions by institutional investors require accurate predictions with respect to the development of stock markets. Motivated by previous research that revealed the unsatisfactory performance of existing stock market prediction models, this study proposes a novel prediction approach. Our proposed system combines Artificial Intelligence (AI) with data from Virtual Investment Communities (VICs) and leverages VICs’ ability to support the process of predicting stock markets. An empirical study with two different models using real data shows the potential of the AI-based system with VICs information as an instrument for stock market predictions. VICs can be a valuable addition but our results indicate that this type of data is only helpful in certain market phases.
This article discusses the counterpart of interactive machine learning, i.e., human learning while being in the loop in a human-machine collaboration. For such cases we propose the use of a Contradiction Matrix to assess the overlap and the contradictions of human and machine predictions. We show in a small-scaled user study with experts in the area of pneumology (1) that machine-learning based systems can classify X-rays with respect to diseases with a meaningful accuracy, (2) humans partly use contradictions to reconsider their initial diagnosis, and (3) that this leads to a higher overlap between human and machine diagnoses at the end of the collaboration situation. We argue that disclosure of information on diagnosis uncertainty can be beneficial to make the human expert reconsider her or his initial assessment which may ultimately result in a deliberate agreement. In the light of the observations from our project, it becomes apparent that collaborative learning in such a human-in-the-loop scenario could lead to mutual benefits for both human learning and interactive machine learning. Bearing the differences in reasoning and learning processes of humans and intelligent systems in mind, we argue that interdisciplinary research teams have the best chances at tackling this undertaking and generating valuable insights.
In the upcoming years, the internet of things (IoT)will enrich daily life. The combination of artificial intelligence(AI) and highly interoperable systems will bring context-sensitive multi-domain services to reality. This paper describesa concept for an AI-based smart living platform with open-HAB, a smart home middleware, and Web of Things (WoT) askey components of our approach. The platform concept con-siders different stakeholders, i.e. the housing industry, serviceproviders, and tenants. These activities are part of the Fore-Sight project, an AI-driven, context-sensitive smart living plat-form.
The recent COVID-19 pandemic represents an unprecedented worldwide event to study the influence of related news on the financial markets, especially during the early stage of the pandemic when information on the new threat came rapidly and was complex for investors to process. In this paper, we investigate whether the flow of news on COVID-19 had an impact on forming market expectations. We analyze 203,886 online articles dealing with COVID-19 and published on three news platforms (MarketWatch.com, NYTimes.com, and Reuters.com) in the period from January to June 2020. Using machine learning techniques, we extract the news sentiment through a financial market-adapted BERT model that enables recognizing the context of each word in a given item. Our results show that there is a statistically significant and positive relationship between sentiment scores and S&P 500 market. Furthermore, we provide evidence that sentiment components and news categories on NYTimes.com were differently related to market returns.
The Dagstuhl Perspectives Workshop "Online Privacy: Towards Informational Self-Determination on the Internet" (11061) has been held in February 6-11, 2011 at Schloss Dagstuhl. 30 participants from academia, public sector, and industry have identified the current status-of-the-art of and challenges for online privacy as well as derived recommendations for improving online privacy. Whereas the Dagstuhl Manifesto of this workshop concludes the results of the working groups and panel discussions, this article presents the talks of this workshop by their abstracts.
With the rapid growth of technology in recent years, we are surrounded by or even dependent on the use of technological devices such as smartphones as they are now an indispensable part of our life. Smartphone applications (apps) provide a wide range of utilities such as navigation, entertainment, fitness, etc. To provide such context-sensitive services to users, apps need to access users' data including sensitive ones, which in turn, can potentially lead to privacy invasions. To protect users against potential privacy invasions in such a vulnerable ecosystem, legislation such as the European Union General Data Protection Regulation (EU GDPR) demands best privacy practices. Therefore, app developers are required to make their apps compatible with legal privacy principles enforced by law. However, this is not an easy task for app developers to comprehend purely legal principles to understand what needs to be implemented. Similarly, bridging the gap between legal principles and technical implementations to understand how legal principles need to be implemented is another barrier to develop privacy-friendly apps. To this end, this paper proposes a privacy and security design guide catalog for app developers to assist them in understanding and adopting the most relevant privacy and security principles in the context of smartphone apps. The presented catalog is aimed at mapping the identified legal principles to practical privacy and security solutions that can be implemented by developers to ensure enhanced privacy aligned with existing legislation. Through conducting a case study, it is confirmed that there is a significant gap between what developers are doing in reality and what they promise to do. This paper provides researchers and developers of privacy-related technicalities an overview of the characteristics of existing privacy requirements needed to be implemented in smartphone ecosystems, on which they can base their work.
Detailed feedback on exercises helps learners become proficient but is time-consuming for educators and, thus, hardly scalable. This manuscript evaluates how well Generative Artificial Intelligence (AI) provides automated feedback on complex multimodal exercises requiring coding, statistics, and economic reasoning. Besides providing this technology through an easily accessible web application, this article evaluates the technology’s performance by comparing the quantitative feedback (i.e., points achieved) from Generative AI models with human expert feedback for 4,349 solutions to marketing analytics exercises. The results show that automated feedback produced by Generative AI (GPT-4) provides almost unbiased evaluations while correlating highly with (r = 0.94) and deviating only 6 % from human evaluations. GPT-4 performs best among seven Generative AI models, albeit at the highest cost. Comparing the models’ performance with costs shows that GPT-4, Mistral Large, Claude 3 Opus, and Gemini 1.0 Pro dominate three other Generative AI models (Claude 3 Sonnet, GPT-3.5, and Gemini 1.5 Pro). Expert assessment of the qualitative feedback (i.e., the AI’s textual response) indicates that it is mostly correct, sufficient, and appropriate for learners. A survey of marketing analytics learners shows that they highly recommend the app and its Generative AI feedback. An advantage of the app is its subject-agnosticism—it does not require any subject- or exercise-specific training. Thus, it is immediately usable for new exercises in marketing analytics and other subjects.
Device-to-device (D2D) communication is an innovative solution for improving wireless network performance to efficiently handle the ever-increasing mobile data traffic. Communication takes place directly between two devices that are in each other’s transmission range. So far, research has focused on the technical challenges of implementing this technology and assumes a user’s general willingness to participate as forwarder in this technology. However, this simplifying assumption is not realistic, as willingness to participate in D2D communication can vary depending on the user. In this work, we consider the scenario that a user can act as a forwarder for a receiver who is not directly or insufficiently reached by the base station and accordingly has no or poor Internet connection. We take a user-centric approach and investigate the willingness to provide an Internet connection as a forwarder. We are the first to investigate user preferences for D2D communication using a choice-based conjoint analysis. Our results, based on a representative sample of potential users (N=181), show that the social relationship between the potential forwarder and the receiver has the greatest impact on the potential forwarder’s decision to provide an Internet connection to the receiver, accepting sacrifices in terms of additional battery consumption and reduced own service performance. In a detailed segment analysis, we observe significant preference differences depending on smartphone usage behavior and user age. Taking the corresponding preferences into account when matching forwarders and receivers can further increase technology adoption.