AI-Enhanced Hybrid Decision Management

2023 | Business & Information Systems Engineering | Citations: 0

Authors: Bork, Dominik; Ali, Syed Juned; Dinev, Georgi Milenov

Abstract: The Decision Model and Notation (DMN) modeling language allows the precise speci ... Expand

Abstract: The Decision Model and Notation (DMN) modeling language allows the precise specification of business decisions and business rules. DMN is readily understandable by business users involved in decision management. However, as the models get complex, the cognitive abilities of humans threaten manual maintainability and comprehensibility. Proper design of the decision logic thus requires comprehensive automated analysis of e.g., all possible cases the decision shall cover; correlations between inputs and outputs; and the importance of inputs for deriving the output. In the paper, the authors explore the mutual benefits of combining human-driven DMN decision modeling with the computational power of Artificial Intelligence for DMN model analysis and improved comprehension. The authors propose a model-driven approach that uses DMN models to generate Machine Learning (ML) training data and show, how the trained ML models can inform human decision modelers by means of superimposing the feature importance within the original DMN models. An evaluation with multiple real DMN models from an insurance company evaluates the feasibility and the utility of the approach. Collapse

Topics: artificial intelligence explainable artificial intelligence perceived usefulness price management extensible markup language

Methods: computational algorithm decision tree classification experiment conceptual modelling simulation

A Reference Architecture for a Workflow Management System Front End Designed for Augmented Reality Headsets

2023 | European Conference On Information Systems | Citations: 0

Authors: Damarowsky, Johannes; Kuehnel, Stephan; Böhmer, Martin; Sackmann, Stefan

Abstract: A well-known approach to managing and controlling workflows in organizations is ... Expand

Abstract: A well-known approach to managing and controlling workflows in organizations is the workflow management system (WFMS). Recently, approaches utilizing augmented reality headsets as WFMS front ends have been discussed, enabling higher efficiency, effectiveness, and usability for certain application scenarios. However, existing design-oriented approaches lack tangible guidance for implementation. A well-known approach to address such knowledge gaps is a reference architecture, which inter alia reduces development times and risks and facilitates collaboration between developers. Based on an existing tentative design theory for an augmented reality-based WFMS front end, we contribute a reference architecture containing an extended design theory, user interface design, and UML models for use cases, components, classes, and sequence flows. The reference architecture was successfully operationalized in a prototype and positively evaluated via a survey of respective users. Collapse

Topics: usability user interface augmented reality smart device enterprise architecture

Methods: design science design artifact unified modeling language business process model and notation modeling language

Theories: unified theory of acceptance and use of technology

SIREN: Designing Business Processes for Comprehensive Industrial IoT Security Management

2023 | DESRIST | Citations: 0

Authors: Hornsteiner, Markus; Schönig, Stefan

Abstract: The Industrial Internet of Things (IIoT) paradigm means that “things” in an indu ... Expand

Abstract: The Industrial Internet of Things (IIoT) paradigm means that “things” in an industrial context are equipped with connectivity. The convergence of formerly isolated Operational Technology with IT provides disruptive opportunities for organizations but is also vulnerable to cyberattacks. To mitigate these risks, the IEC62443 standard was developed, which will be mandatory for critical infrastructure organizations due to the EU Cybersecurity Act. This standard demands various requirements for the technology and organizational aspects of organizations. To implement the standard’s technical requirements and demonstrate compliance, applications can be used. This paper utilizes Design Science Research (DSR) to design, develop, and demonstrate Security Iiot pRocEss Notation (SIREN), an approach based on Business Process Model and Notation (BPMN) to model and monitor processes and compliance. Previous research have yet to cover the IIoT explicitly and lack the monitoring of the modeled attributes. Therefore, a novel specialized approach is presented, enhancing the model with monitorable attributes based on the standard. Thus, this paper presents a BPMN-based approach to model and monitor security-aware processes in IIoT. Collapse

Topics: Python evaluation criteria extensible markup language IT security requirements analysis

Methods: modeling language business process model and notation business process modeling personal interview design artifact

Building a deep learning-based QA system from a CQA dataset

2023 | Decision Support Systems | Citations: 0

Authors: Jin, Sol; Lian, Xu; Jung, Hanearl; Park, Jinsoo; Suh, Jihae

Abstract: A man-made machine-reading comprehension (MRC) dataset is necessary to train the ... Expand

Abstract: A man-made machine-reading comprehension (MRC) dataset is necessary to train the answer extraction part of existing Question Answering (QA) systems. However, a high-quality and well-structured dataset with questionparagraph-answer pairs is not usually found in the real world. Furthermore, updating or building an MRC dataset is a challenging and costly affair. To address these shortcomings, we propose a QA system that uses a large-scale English Community Question Answering (CQA) dataset (i.e., Stack Exchange) composed of 3,081,834 questionanswer pairs. The QA system adopts a classifier-retriever-summarizer structure design. The question classifier and the answer retriever part are based on a Bidirectional Encoder Representations from Transformers (BERT) Natural Language Processing (NLP) model by Google, and the summarizer part introduces a deep learning-based Text-to-Text Transfer Transformer (T5) model to summarize the long answers. We instantiated the proposed QA system with 140 topics from the CQA dataset (including topics such as biology, law, politics, etc.) and conducted human and automatic evaluations. Our system presented encouraging results, considering that it provides highquality answers to the questions in the test set and satisfied the requirements to develop a QA system without MRC datasets. Our results show the potential of building automatic and high-performance QA systems without being limited by man-made datasets, a significant step forward in the research of open-domain or specificdomain QA systems. Collapse

Topics: privacy decision making online community IT productivity Google+

Methods: BERT chatGPT computational algorithm experiment natural language processing

A Prototype to Support Business Model Innovation through Crowdsourcing and Artificial Intelligence

2023 | International Conference on Business Informatics | Citations: 0

Authors: Klippenstein, Arthur; Weskamp, Dr Christoph; Laux, Florian; Neuhaus, Florian; Pfannschmidt, Karlson; Bülling, Melissa; Kassanke, Dr Stephan

Abstract: The development of new and innovative business models is a central challenge fo ... Expand

Abstract: The development of new and innovative business models is a central challenge for many companies, particularly for small and medium-sized companies. Information systems could support these companies by actively guiding them through a business model development process. However, the existing business model development tools only provide passive support for their users (e.g., digital whiteboards). Therefore, we set out to develop a prototype that actively supports its users by generating business model ideas. Informed by an existing design theory, we built a prototype relying on hybrid intelligence (i.e., the combination of human and artificial knowledge). The prototype iteratively generates new business model ideas by recombining existing knowledge, posts the ideas to a crowdsourcing platform for evaluation, and learns from the crowds' evaluation. This demonstration paper presents the prototype, the challenges we faced during its implementation, and directions for future research on machine-supported business model development. Collapse

Topics: business model crowdsourcing user interface usability value creation

Methods: design artifact design theory machine learning focus group survey

Theories: socio technical theory

Experts vs. Nonexperts in Online Crowdfunding Markets

2023 | Management Information Systems Quarterly | Citations: 0

Authors: Lin, Mingfeng; Sias, Richard; Wei, Zaiyan

Abstract: The growth of crowdfunding markets that include both expert and nonexpert inves ... Expand

Abstract: The growth of crowdfunding markets that include both expert and nonexpert investors will soon accelerate due to recent changes in Securities Exchange Commission (SEC) regulations. Prior work has suggested that nonexperts (1) may benefit from experts' participation via mimicking their trades, but (2) will also face a cost, as experts crowding nonexperts out of the best opportunities will ensure that nonexperts will suffer lower returns than experts. Traditional economic theory holds that the crowding effect means that the relative importance of nonexperts in the market will decline over time until they become unimportant. Exploiting a unique period in one crowdfunding market (Prosper.com) that allowed us to directly estimate the net cost of competing with better-informed experts, we found that the net negative effects of expert participation on nonexperts are small. We used simulations to both better understand (1) the market characteristics and crowdfunding platform choices that influence experts' and nonexperts' returns, their return gap, and the extent to which nonexperts are better or worse off relative to a market without expert participation, and (2) the factors that may contribute to the small expert/nonexpert Prosper return gap. Collapse

Topics: crowdsourcing Prosper crowdfunding extensible markup language accounting

Methods: simulation descriptive statistic logistic regression experiment computational algorithm

Theories: economic theory

Cyber-risk Management Framework for Online Gaming Firms: an Artificial Neural Network Approach

2023 | Information Systems Frontiers | Citations: 0

Authors: Sharma, Kalpit; Mukhopadhyay, Arunabha

Abstract: Hackers have used Distributed-Denial-of-Service attacks to overwhelm a firm’s cy ... Expand

Abstract: Hackers have used Distributed-Denial-of-Service attacks to overwhelm a firm’s cyber-resources resulting in disrupted access to legitimate end-users. Globally, DDoS attacks cost firms between US$ 120 K to US$ 2 M for each incident. Apart from the monetary loss, they also disrupt service quality and damage the brand reputation of firms. In 2018-2019, Massively Multiplayer Online Gaming (MMOG) firms witnessed 74% of the total DDoS attacks. MMOG firms form a lucrative segment for hackers because of their large customer base and the massive incentive to cause disruptions and losses. Our Feedforward Neural Network-based Cyber-risk Assessment and Mitigation (FNN-CRAM) model consists of three modules: assessment, quantification, and mitigation. The cyber-risk assessment module uses FNN, which takes seven inputs comprising DDoS attack intensity and duration for five DDoS attack types, vulnerability data (i.e., their counts and score), and the vulnerability trends over time. This layer is connected to a ten-neuron hidden layer and one neuron output layer that estimates the probability of these attacks. We also observe that the probability of these DDoS attacks follows a Weibull distribution. Next, our cyber-risk quantification module computes the expected loss. We note that expected losses due to these DDoS attacks follow a gamma distribution. Our cyber-risk mitigation module uses a heat matrix to help the CTO (i) prioritize the cyber-risk associated with a DDoS attack and (ii) decide whether to reduce, accept, or pass the cyber-risk using technological and cyber-insurance interventions. Collapse

Topics: denial of service attack IT security risk management IT security threat extensible markup language

Methods: artificial neural network descriptive statistic logistic regression k-nearest neighbor support vector machine

DyPolDroid: Protecting Against Permission-Abuse Attacks in Android

2023 | Information Systems Frontiers | Citations: 0

Authors: Rubio-Medrano, Carlos E.; Soundrapandian, Pradeep Kumar Duraisamy; Hill, Matthew; Claramunt, Luis; Baek, Jaejong; S, Geetha; Ahn, Gail-Joon

Abstract: Android applications are extremely popular, as they are widely used for banking, ... Expand

Abstract: Android applications are extremely popular, as they are widely used for banking, social media, e-commerce, etc. Such applications typically leverage a series of Permissions, which serve as a convenient abstraction for mediating access to security-sensitive functionality within the Android Ecosystem, e.g., sending data over the Internet. However, several malicious applications have recently deployed attacks such as data leaks and spurious credit card charges by abusing the Permissions granted initially to them by unaware users in good faith. To alleviate this pressing concern, we present DyPolDroid, a dynamic and semi-automated security framework that builds upon Android Enterprise, a device-management framework for organizations, to allow for users and administrators to design and enforce so-called Counter-Policies, a convenient user-friendly abstraction to restrict the sets of Permissions granted to potential malicious applications, thus effectively protecting against serious attacks without requiring advanced security and technical expertise. Additionally, as a part of our experimental procedures, we introduce Laverna, a fully operational application that uses permissions to provide benign functionality at the same time it also abuses them for malicious purposes. To fully support the reproducibility of our results, and to encourage future work, the source code of both DyPolDroid and Laverna is publicly available as open-source. Collapse

Topics: mobile application Android bring your own device digital distribution mobile application market

Methods: experimental task computational algorithm experiment design artifact literature study

Dividing Complexity to Conquer New Dimensions – Towards a Framework for Designing Augmented Reality Solutions

2022 | Americas Conference on Information Systems | Citations: 0

Authors: Bräker, Julia; Semmann, Martin

Abstract: Augmented reality (AR) can foster service innovation and thus cope with some of ... Expand

Abstract: Augmented reality (AR) can foster service innovation and thus cope with some of the most urgent challenges in the service science domain, namely supporting frontline workers while ensuring high safety standards. Therefore, the utilization of AR can help to achieve these goals. On the contrary, AR remains a complex technology with specific requirements and preconditions that demand expertise to overcome them. Based on a case study, we derive a framework for designing AR solutions, which helps divide the complexity of designing and developing AR-based services to support the adoption and diffusion of AR applications. Such an encompassing perspective on initial AR explorations helps to transform the acquired information into a thorough proof of concept, pilot implementations and ultimately productive software. Collapse

Topics: augmented reality computer hardware logistics management smart device mobile application

Methods: design framework case study qualitative interview design artifact survey

AI-Based Vehicular Network toward 6G and IoT: Deep Learning Approaches

2022 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Chen, Mu-Yen; Fan, Min-Hsuan; Huang, Li-Xiang

Abstract: In recent years, vehicular networks have become increasingly large, heterogeneou ... Expand

Abstract: In recent years, vehicular networks have become increasingly large, heterogeneous, and dynamic, making it difficult to meet strict requirements of ultralow latency, high reliability, high security, and massive connections for next generation (6G) networks. Recently, deep learning (DL) has emerged as a powerful artificial intelligence (AI) technique to optimize the efficiency and adaptability of vehicle and wireless communication. However, rapidly increasing absolute numbers of vehicles on the roads are leading to increased automobile accidents, many of which are attributable to drivers interacting with their mobile phones. To address potentially dangerous driver behavior, this study applies deep learning approaches to image recognition to develop an AI-based detection system that can detect potentially dangerous driving behavior. Multiple convolutional neural network (CNN)-based techniques including VGG16, VGG19, Densenet, and Openpose were compared in terms of their ability to detect and identify problematic driving. Collapse

Topics: extensible markup language enterprise architecture Python open source evaluation criteria

Methods: machine learning deep learning experiment convolutional neural network TensorFlow