Business Inferences and Risk Modeling with Machine Learning; The case of Aviation Incidents

2023 | HICSS | Citations: 0

Authors: Cankaya, B.; Topuz, K.; Glassman, A.

Abstract: Machine learning becomes truly valuable only when decision-makers begin to depe ... Expand

Abstract: Machine learning becomes truly valuable only when decision-makers begin to depend on it to optimize decisions. Instilling trust in machine learning is critical for businesses in their efforts to interpret and get insights into data, and to make their analytical choices accessible and subject to accountability. In the field of aviation, the innovative application of machine learning and analytics can facilitate an understanding of the risk of accidents and other incidents. These occur infrequently, generally in an irregular, unpredictable manner, and cause significant disruptions, and hence, they are classified as "highimpact, low-probability" (HILP) events. Aviation incident reports are inspected by experts, but it is also important to have a comprehensive overview of incidents and their holistic effects. This study provides an interpretable machine-learning framework for predicting aircraft damage. In addition, it describes patterns of flight specifications detected through the use of a simulation tool and illuminates the underlying reasons for specific aviation accidents. As a result, we can predict the aircraft damage with 85% accuracy and 84% in-class accuracy. Most important, we simulate a combination of possible flight-type, aircraft-type, and pilot-expertise combinations to arrive at insights, and we recommend actions that can be taken by aviation stakeholders, such as airport managers, airlines, flight training companies, and aviation policy makers. In short, we combine predictive results with simulations to interpret findings and prescribe actions.A machine-learning (ML) algorithm was chosen for its fast performance, short run-time, and interpretability. The ML algorithms were compared and evaluated on a confusion matrix for their mean receiver operating characteristic curve (ROC), Collapse

Topics: decision making decision support system graphical user interface usability missing data

Methods: simulation machine learning multinomial logistic regression computational algorithm support vector machine

Pair Analytics in a Visual Analytics Context

2023 | HICSS | Citations: 0

Authors: Fisher, B.; Kasik, D.

Abstract: This case study details the development of "pair analytics" as practical approa ... Expand

Abstract: This case study details the development of "pair analytics" as practical approach to applied analysis and as a scientific research method. The hybrid research project itself was part of a larger research program approved for the Canadian government for their offset program and supported by Federal and Provincial research internships. As a real-world analysis approach, the pair analysis sessions conduced actionable causal chain analysis of aircraft safety. As a scientific method, pair analytics advanced our knowledge of the cognitive science of interpersonal communication in Joint Activities. The paper describes how aerospace researchers and cognitive scientists were able to design a research approach that met constraints from both areas. It concludes with discussion of the implications of this work for highly integrated basic and responsive research in other areas of visualization and analytics. Collapse

Topics: visual analytics crowdsourcing

Methods: exploratory data analysis ethnography case study laboratory experiment grounded theory

Theories: activity theory theory of distributed cognition

Touching Space: Distributed Ledger Technology for Tracking and Tracing Certificates

2023 | HICSS | Citations: 1

Authors: Moriggl, Pascal; Asprion, Petra; Schneider, Bettina; Scherb, Christopher

Abstract: Components built into space vehicles and equipment (space products) must meet di ... Expand

Abstract: Components built into space vehicles and equipment (space products) must meet different regulatory requirements; in detail, each component must be certified and sustainably traceable at all times. Space engineers have expressed the need for an interoperable system to collect, manage and route certifications for components, parts and materials that go into space products. The lack of a unified approach in the European space industry is a challenge for companies involved in product development. This research proposes an open-source, secure, fast and distributed ledger technology (DLT) based solution that fits into any IT environment and is well adapted to the needs of manufacturing companies in the space sector. The results show that a blockchain-based solution based on 'Hyperledger Fabric' combined with the InterPlanetary File System is viable. The results can guide other researchers and practitioners to consider DLTs when changing their certification management paradigm with suppliers, customers and auditors. Collapse

Topics: blockchain JavaScript authorization business process management graphical user interface

Methods: design artifact literature study qualitative interview

Knowledge management mechanisms and common knowledge impacts on the value of knowledge at individual and organizational levels

2023 | International Journal of Information Management | Citations: 0

Authors: Sabherwal, Rajiv; Steelman, Zach; Becerra-Fernandez, Irma

Abstract: Knowledge management (KM) impacts have typically been examined on the value of k ... Expand

Abstract: Knowledge management (KM) impacts have typically been examined on the value of knowledge to organizations but not individuals. This paper uses survey data (186 employees) and qualitative data (300 + employees) at the National Aeronautics and Space Administration to examine the effects of four KM mechanisms (social learning, learning from others through IT, learning from IT, and IT-based knowledge substitution) and common knowledge on the individual and organizational value of knowledge. The results indicate that common knowledge and the two interpersonal mechanisms (social learning, learning from others through IT) enhance the perceived value of knowledge at both levels, but both mechanisms that rely on IT for the knowledge (learning from IT, IT-based knowledge substitution) reduce the perceived knowledge value at one level and have no significant effect at the other level. Further, common knowledge strengthens the positive effects of both interpersonal mechanisms, and weakens the negative effects of IT-based knowledge substitution, on perceived value of knowledge at both levels. Collapse

Topics: organizational value explicit knowledge IS impact knowledge sharing service desk

Methods: qualitative interview chi squared test focus group structural equation modeling design artifact

Theories: assimilation theory of learning

The Primordial Soup: Exploring the Emotional Microfoundations of Cluster Genesis

2022 | Organization Science | Citations: 0

Authors: Aversa, Paolo; Furnari, Santi; Jenkins, Mark

Abstract: Previous research on the genesis of industrial clusters has focused on macroleve ... Expand

Abstract: Previous research on the genesis of industrial clusters has focused on macrolevel (e.g., agglomeration economies and institutions) or mesolevel explanatory factors (e.g., serial entrepreneurship, spin-offs). Less studied are the microfoundations of cluster genesis, intended as the individual- and group-level processes underlying such macrolevel outcomes. Yet, microfoundations are key to understanding the “primordial soup” of cluster genesis—that is, the processes unfolding in the early moments of cluster formation, before the first emergence of commercial activity. Through a historical case study of the British Motorsport Valley (1911–1970s), we trace back the primordial origins of this cluster to the casual leisure activities of groups of amateur motorsport enthusiasts who then prompted the professionalization of motorsport racing and its transformation into the business at the core of the industrial cluster. We theorize that clusters emerge through the layering of different domains (casual leisure, serious leisure, and business), each made of three elements (actors, activities, and artifacts), which interact via two microlevel mechanisms: (1) localizing passion, a shared emotional energy by which people become affectively attached to the spaces where they carry out activities that they enjoy; (2) domain repurposing, the shift of a configuration of actors, activities, and artifacts toward a new purpose, originating a new domain. Whereas domain repurposing induces the transformation of activities from leisure to business (thus originating the industry at the core of a cluster), localizing passion anchors the activities to the same geographical area (clustering the industry). Our key contribution is to explore the emotional microfoundations of cluster genesis. Collapse

Topics: knowledge sharing database system intrinsic motivation Google+ entrepreneurship

Methods: qualitative interview archival research business process modeling theory development cluster analysis

Theories: theory of dominant design

Employee perspectives on value realization from data within data-driven business models

2022 | Electronic Markets | Citations: 0

Authors: Förster, Matthias; Bansemir, Bastian; Roth, Angela

Abstract: Firms are innovating data-driven business models (DDBMs) to realize value from d ... Expand

Abstract: Firms are innovating data-driven business models (DDBMs) to realize value from data. Yet, making DDBMs work is challenging, and DDBMs often fall short of expected value realization. One reason for this shortfall is that firms do not know how employees, who decisively influence a DDBM’s value realization, view this complex and multi-facetted topic. We think it is necessary to understand the employees’ perspectives, the dimensions that build these perspectives and the characteristics employees are particularly interested in regarding value realization from data. We address this research gap by applying the Q-methodology to examine the perspectives among 70 employees across twelve DDBMs at a German automotive manufacturer. This yields eight perspectives, e.g., data advocacy, data caution or data practical. By exploring these perspectives, we provide a first groundwork on how employees view and appraise value realization from data which adds to the strive for mastering value realization from data within DDBMs. Collapse

Topics: anonymity organizational value innovation management analytical information system data-driven business model

Methods: qualitative interview factor analysis Q methodology qualitative coding archival research

Theories: stakeholder theory

Transformer-based Summarization and Sentiment Analysis of SEC 10-K Annual Reports for Company Performance Prediction

2022 | HICSS | Citations: 0

Authors: Hsieh, Hsin-Ting; Hristova, Diana

Abstract: Annual reports published by companies contain important insights regarding their ... Expand

Abstract: Annual reports published by companies contain important insights regarding their performance and are often analyzed in a manual, subjective manner. We address this point by combining the streams of research on text summarization and topic modelling with the one on sentiment analysis. Our approach consists of the steps of text summarization using BERTSUMEXT, topic modelling with LDA, sentiment analysis with FinBERT, and performance prediction with Decision Trees and Random Forest. The result provides decision makers with an interpretable and condensed representation of the content of annual reports, together with its relationship to future company performance. We evaluate our approach on 10-K reports, demonstrating both its interpretability for analysts and explanatory power regarding future company performance. Collapse

Topics: organizational productivity data breach cloud computing Python explainable artificial intelligence

Methods: sentiment analysis topic model machine learning BERT decision tree classification

Impact of IT governance process capability on business performance: Theory and empirical evidence

2022 | Decision Support Systems | Citations: 1

Authors: Joshi, Anant; Benitez, Jose; Huygh, Tim; Ruiz, Laura; De Haes, Steven

Abstract: In the digital economy, firms’ IT resource investments represent a significant p ... Expand

Abstract: In the digital economy, firms’ IT resource investments represent a significant portion of their capital investments. IT governance processes are critical for companies to decide what and how to deploy IT resources and measure and achieve the expected business benefits. This study introduces and measures the concept of IT governance process capability, which is defined as the firm’s ability to identify, design, implement and leverage the following IT governance processes: IT decision-making, IT planning, IT infrastructure modernization, IT services delivery, and IT monitoring. We propose that IT governance process capability can improve IT performance, which in turn can improve business performance. Using a unique dataset from 881 global companies, we found support for the proposed research model. This paper contributes to the Information Systems (IS) literature on business value of IT by conceptualizing, evaluating, and introducing the construct of IT governance process capability and theorizing and proving how this core IT capability positively affects IT performance to enhance business performance. Collapse

Topics: IT governance organizational productivity IT productivity COBIT organizational value

Methods: survey theory development triangulation partial least squares regression statistical hypothesis test

Online Reviews in B2B Markets: A Qualitative Study of Underlying Motives

2022 | European Conference On Information Systems | Citations: 0

Authors: Seutter, Janina

Abstract: While online reviews in and markets have reached an advanced state of maturity ... Expand

Abstract: While online reviews in and markets have reached an advanced state of maturity in both academia and practice, the study of the dynamics of online reviews in the B2B market is still in its early stages. For this market, there are numerous unanswered questions concerning online reviews. The growing number of B2B review platforms and reviews makes it increasingly important to better understand the heterogeneous motives for writing online reviews for a business partner. Structured by the scales of the Motivation Sources Inventory, the literature on online reviews in the B2C market, and specifically the motivation underpinning review writing, and the characteristics of B2B review platforms, a semi-structured interview protocol is derived and presented. This research-in-progress describes the concept and proposed next steps of a qualitative study aimed at identifying the underlying motives for writing B2B online reviews. Collapse

Topics: business-to-business online review user-generated content IT career business-to-consumer

Methods: qualitative interview personal interview survey qualitative content analysis grounded theory

Recorded Work Meetings and Algorithmic Tools: Anticipated Boundary Turbulence

2021 | HICSS | Citations: 0

Authors: Cardon, Peter; Ma, Haibing; Fleischmann, A. Carolin; Aritz, Jolanta

Abstract: Meeting recordings and algorithmic tools that process and evaluate recorded meet ... Expand

Abstract: Meeting recordings and algorithmic tools that process and evaluate recorded meeting data may provide many new opportunities for employees, teams, and organizations. Yet, the use of this data raises important consent, data use, and privacy issues. The purpose of this research is to identify key tensions that should be addressed in organizational policymaking about data use from recorded work meetings. Based on interviews with 50 professionals in the United States, China, and Germany, we identify the following five key tensions (anticipated boundary turbulence) that should be addressed in a social contract approach to organizational policymaking for data use of recorded work meetings: disruption versus help in relationships, privacy versus transparency, employee control versus management control, learning versus evaluation, and trust in AI versus trust in people. Collapse

Topics: artificial intelligence privacy General Data Protection Regulation legal context productivity

Methods: qualitative interview literature study personal interview computational algorithm