Challenges in the Model Development Process: Discussions with Data Scientists

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

Authors: Gerhart, Natalie; Torres, Russell; Giddens, Laurie

Abstract: Businesses are increasingly seeking out analytics to improve decision-making pr ... Expand

Abstract: Businesses are increasingly seeking out analytics to improve decision-making processes, although often with hesitations. Decision makers often do not have the sophisticated analytical skills needed to fully understand the analytics process. Contrastingly, data scientists may lack the business acumen needed to fully grasp the business context of the decision. In this research, we consider the perspective of the data scientist through a series of interviews to draw out challenges in the analytics process. We use principal-agent theory as a lens to shape our understanding of the conflict that arises due to goal misalignment and information asymmetry between the principal and agent. Findings are presented in the CRISP-DM process and a future research agenda is proposed. Collapse

Topics: decision making implicit knowledge data quality organizational impact organizational memory

Methods: Cross-Industry Standard Process for Data Mining qualitative interview theory development mathematical model literature study

Theories: agency theory lemon market theory theory of bounded rationality

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

Machine Learning in Transaction Monitoring: The Prospect of xAI

2023 | HICSS | Citations: 0

Authors: Gerlings, Julie; Constantiou, Ioanna

Abstract: Banks hold a societal responsibility and regulatory requirements to mitigate the ... Expand

Abstract: Banks hold a societal responsibility and regulatory requirements to mitigate the risk of financial crimes. Risk mitigation primarily happens through monitoring customer activity through Transaction Monitoring (TM). Recently, Machine Learning (ML) has been proposed to identify suspicious customer behavior, which raises complex socio-technical implications around trust and explainability of ML models and their outputs. However, little research is available due to its sensitivity. We aim to fill this gap by presenting empirical research exploring how ML supported automation and augmentation affects the TM process and stakeholders’ requirements for building eXplainable Artificial Intelligence (xAI). Our study finds that xAI requirements depend on the liable party in the TM process which changes depending on augmentation or automation of TM. Context-relatable explanations can provide much-needed support for auditing and may diminish bias in the investigator’s judgement. These results suggest a use case-specific approach for xAI to adequately foster the adoption of ML in TM. Collapse

Topics: explainable artificial intelligence decision making electronic mail

Methods: qualitative interview machine learning random forest classification qualitative coding action research

Introduction to the Minitrack on Software Sustainability: Strategies for Long-Lasting and Usable Software

2023 | HICSS | Citations: 0

Authors: Gesing, Sandra; Dahan, Maytal; Stubbs, Joe

Abstract: The focus on software usability, long-lasting and reproducible software is a ti ... Expand

Abstract: The focus on software usability, long-lasting and reproducible software is a timely one that spans various domains of science and significant investment of research funding across the US, Europe, U.K, and elsewhere. The three concepts -usability, sustainability and reproducibility are interconnected with each other and cover a wide range of application areas. They affect all layers of the software processfrom enabling reproducing experiments via an easy user interface to using containerization for application portability. This minitrack focused on the broad spectrum of submissions that deal with complex scenarios such as containerization, strategies for long-lasting software, usability and user interface issues, handling data curation and provenance and more. Collapse

Methods: literature sample

Introduction to the Minitrack Digital Innovations for the Aging Society

2023 | HICSS | Citations: 0

Authors: Gewald, H.; Bozan, K.; Vogel, D.

Abstract: ... Expand

Abstract: Collapse

Topics: information system use

Methods: literature study structured literature research

Framing as an App-Design Measure to Nudge Users Toward Infection Disclosure in Contact-Tracing Applications

2023 | European Conference On Information Systems | Citations: 0

Authors: Ghaffar, Abdul Muqeet; Widjaja, Thomas

Abstract: Contact-tracing applications are only effective in countering pandemics when tw ... Expand

Abstract: Contact-tracing applications are only effective in countering pandemics when two conditions are fulfilled: A) they are widely adopted, and B) users voluntarily disclose their infection to warn others. While much research has investigated how contact-tracing applications should be designed and promoted to motivate app-adoption, little is known about how to increase voluntary infection disclosures. To increase the voluntary infection disclosure among app-users, our joint research project with the core development team of a contact-tracing application relied on the theory of message framing to investigate how to nudge users toward infection disclosure in contact-tracing applications. Based on a mixed method research design consisting of 15 workshops with the core development team of the contact-tracing application and a conjoint study among 139 users of a European contact-tracing application we show that message framing can be a useful approach to increase the voluntary infection disclosure in contact-tracing applications. Collapse

Topics: privacy mobile application pandemic self efficacy internet technology

Methods: survey conjoint analysis mixed method survey design Student's t-test

Towards a Theory to Explain Prosocial Data Disclosure - An Explorative Investigation of the Antecedents of Infection Disclosure

2023 | International Conference on Information Systems | Citations: 0

Authors: Ghaffar, Abdul Muqeet; Widjaja, Thomas

Abstract: ... Expand

Abstract: Collapse

Topics: privacy pandemic mobile application knowledge sharing anonymity

Methods: survey structured literature research personal interview literature sample qualitative coding

Theories: privacy calculus theory

Effort as investment in healthcare dialogue-based agents: On the role of means-goal configurations

2023 | Decision Support Systems | Citations: 0

Authors: Ghasemi, Ehsan; Sheikh-Zadeh, Alireza; Song, Jaeki

Abstract: The recent pandemic and resultant increase in clinical caseload have brought dia ... Expand

Abstract: The recent pandemic and resultant increase in clinical caseload have brought dialogue-based agents (DBAs) to the forefront of attention in the healthcare industry. The ability of these agents to accomplish a variety of sequential and related tasks within a single application software has made them more effortful and complex. While effort requirements and complexity of information systems are generally considered negative attributes, the potential effect of user effort investment on user perceptions and decisions is less investigated. Within the framework of goal systems theory, this study explores how perceived effort could be appropriated to enhance users’ positive perceptions and willingness to accept healthcare DBAs outputs. We find evidence for the positive role both in the perceived effort before and after the actual use of healthcare DBAs as well as in user goal magnitude and means-goal configuration on perceptions of usefulness and probability of considering outputs. Collapse

Topics: technology adoption mobile application user experience decision making mobile phone

Methods: experiment regression analysis method experimental group linear regression analysis descriptive statistic

Theories: general systems theory

The Role of Parents’ Mores on Their Intentions to Enroll Their Children in a School-based Telemedicine Program

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

Authors: Ghashami, Farnaz; Gantz, Christopher; Gefen, David

Abstract: Hospitals providing nurse-run school telemedicine programs can improve children ... Expand

Abstract: Hospitals providing nurse-run school telemedicine programs can improve children's access to healthcare services by delivering such services on school premises. Despite this potential, the enrollment in such programs by parents falls short of expectations because of parents' hesitation to allow their children to receive such telemedicine healthcare services. This study investigates some aspects of the role of parents' perception of contributing to a good cause, i.e., personal mores, on their intentions to enroll their children in such a telemedicine program. Surveying parents about such a new telemedicine service that is being deployed in their school district shows that parents' personal mores are associated with increased intentions over and above its expected time-flexibility advantages. Surprisingly, trust increased intentions was fully mediated by those mores. Practical and theoretical implications are discussed, especially that doing good to others may be another reason why people adopt telemedicine, suggesting another reason beyond the utilitarian, rational, and social processes that are portrayed in previous research. Collapse

Topics: behavioral intention electronic health technology adoption missing data healthcare data

Methods: survey qualitative interview SEM tool post-hoc analysis descriptive statistic

Communication of post-release plans in crowdfunding development initiatives: A signaling perspective

2023 | International Journal of Information Management | Citations: 0

Authors: Ghobadi, Shahla

Abstract: Significant research explores how developers leverage crowdfunding to attract fi ... Expand

Abstract: Significant research explores how developers leverage crowdfunding to attract finance for releasing digital goods. However, researchers seldom study “post-release activities” that are crucial for maintaining and advancing those goods. This article elaborates on the challenging nature of post-release activities for crowd­ funding initiatives, asking how developers communicate their post-release plans to effectively prepare backers for possible changes. Using a grounded approach that connects the longitudinal history of fundraising to development to post-release, I examine initiatives that achieved impressive fundraising and development results yet varied significantly in their post-release outcomes. While they consistently signaled post-release plans, the differences are the signals’ costs, backers’ reactions, and the post-release activities and outcomes. I present theoretical propositions that (1) developers benefit in the long run by combining high-cost signaling with engaging backers in follow-up conversations about post-release issues and (2) prospective backers can utilize developers’ communication to identify their post-release signals. Unlike dominant research findings about sig­ nals’ impacts on mobilizing resources during fundraising, the findings emphasize signals’ post-release conse­ quences for stakeholders. While different signaling approaches can enhance short-term performance, they also seed contrasting longer-term outcomes for developers, backers, and the industry. These findings advance knowledge on effective strategies for engaging society to build sustainable digital goods. Collapse

Topics: crowdsourcing crowdfunding digital good Twitter strategic management

Methods: longitudinal research case study grounded theory theory development cross sectional research