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

Adopting Learning Analytics to Inform Postgraduate Curriculum Design: Recommendations and Research Agenda

2023 | Information Systems Frontiers | Citations: 0

Authors: Dennehy, Denis; Conboy, Kieran; Babu, Jaganath

Abstract: Understanding student sentiment plays a vital role in understanding the changes ... Expand

Abstract: Understanding student sentiment plays a vital role in understanding the changes that could or should be made in curriculum design at university. Learning Analytics (LA) has shown potential for improving student learning experiences and supporting teacher inquiry. Yet, there is limited research that reports on the adoption and actual use of LA to support teacher inquiry. This four-year longitudinal study captures sentiment of postgraduate students at a university in Ireland, by integrating LA with the steps of teacher inquiry. This study makes three important contributions to teaching and learning literature. First, it reports on the use of LA to support teacher inquiry over four one-year cycles of a Master of Science in Business Analytics programme between 2016 and 2020. Second, it provides evidence-based recommendations on how to optimise LA to support teacher inquiry, with specific attention as to how these can improve the assimilation of LA into the curriculum design and delivery. Third, the paper concludes with a research agenda to help improve the adoption and integration of LA in the future. Collapse

Topics: innovation management Tableau software analytical information system interactive data visualization Python

Methods: qualitative interview Cross-Industry Standard Process for Data Mining sentiment analysis case study design framework

Theories: assimilation theory of learning

Sustaining Open Source Communities by Understanding the Influence of Discursive Manifestations on Sentiment

2023 | Information Systems Frontiers | Citations: 0

Authors: Dennehy, Denis; Conboy, Kieran; Ferreira, Jennifer; Babu, Jaganath

Abstract: Sustaining open source (OS) communities is fundamental to the long-term success ... Expand

Abstract: Sustaining open source (OS) communities is fundamental to the long-term success of any open source software (OSS) project. An OSS project consists of a community of software developers who are part of a larger business ecosystem involving hardware and software companies. Peer review of software code, known as patch review comments, is an important quality assurance activity for OSS development that requires developers to provide feedback concerning their degree of satisfaction. Despite the importance of feedback, which can affect sentiment of OS communities, the underlying discourse has not been studied. In this study, we use Activity Theory to identify and categorise 20,651 discursive manifestations of contradictions that occurred in patch review comments of a large, evolving OS community. Unique community-specific expressions are identified and mapped to developers’ sentiment during a software release cycle. The study contributes new insights concerning discursive manifestations of contradictions as a driving force for sustaining OS communities. Collapse

Topics: software developer Python electronic mail

Methods: sentiment analysis Cross-Industry Standard Process for Data Mining computational algorithm descriptive statistic theoretical contribution

Theories: activity theory

Toward the Sustainable Development of Machine Learning Applications in Industry 4.0

2023 | European Conference On Information Systems | Citations: 0

Authors: Ellenrieder, Sara; Jourdan, Nicolas; Biegel, Tobias; Cassoli, Beatriz; Metternich, Joachim; Buxmann, Peter

Abstract: As the level of digitization in industrial environments increases, companies ar ... Expand

Abstract: As the level of digitization in industrial environments increases, companies are striving to improve efficiency and resilience to unplanned disruptions through the development of Machine Learning (ML)based applications. Still, sustainable deployment and operation beyond proofs-of-concept is a challenging and resource-intensive task in dynamic enviroments such as industry 4.0, often impeding practical adoption in the long-term and thus sustainable ML product development. In this work, we systematically identify these challenges based on the CRISP-ML process model phases by applying a design science research approach. To this end, we conducted 15 interviews with data science practitioners in industry 4.0. Following a qualitative content analysis, design requirements and design principles for the development and sustainable long-term deployment of ML systems are derived to address identified challenges such as robustness to, and management of data drift caused by timedependencies and machine/product differences, missing metadata, interfaces to other IT systems, expectation management, and MLOps guidelines. Collapse

Topics: production management industry 4.0 systems design systems development new product development

Methods: qualitative interview business process modeling design requirement design principle Cross-Industry Standard Process for Data Mining

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

FINFLUENCERS: OPINION MAKERS OR OPINION FOLLOWERS?

2023 | European Conference On Information Systems | Citations: 0

Authors: Haase, Frederic; Rath, Oliver; Kurka, Marco; Schoder, Detlef

Abstract: This paper explores the concept of Finfluencers: financial social network actor ... Expand

Abstract: This paper explores the concept of Finfluencers: financial social network actors with high potential social influence. Our research aims to clarify whether Finfluencers drive or are influenced by the broader social network sentiment, thereby establishing their role as either opinion makers or opinion followers. Using a dataset of 71 million tweets focusing on stocks and cryptocurrencies, we grouped actors by their social networking potential (SNP). Next, we derived sentiment time series using state-ofthe-art sentiment models and applied the technique of Granger causality. Our findings suggest that the sentiment of Finfluencer actors on Twitter has short-term predictive power for the sentiment of the larger group of actors. We found stronger support for cryptocurrencies in comparison to stocks. From the perspective of financial market regulation, this study emphasizes the relevance of understanding sentiment on social networks and high social influence actors to anticipate scams and fraud. Collapse

Topics: Twitter social network social influence cryptocurrency social media

Methods: longitudinal research time series analysis Granger causality descriptive statistic sentiment analysis

ARTIFICIAL INTELLIGENCE-AUGMENTED DECISION MAKING IN SUPPLY CHAIN MONITORING: AN ACTION DESIGN RESEARCH STUDY

2023 | European Conference On Information Systems | Citations: 0

Authors: Herath Pathirannehelage, Savindu; Jóhannsson, Jóhann; Shrestha, Yash; Krogh, Georg von

Abstract: Organizations are progressively adopting hybrid human-artificial intelligence ( ... Expand

Abstract: Organizations are progressively adopting hybrid human-artificial intelligence (AI) systems in decisionmaking processes, with human decisions being augmented by AI insights. Among the promising AI applications in supply chain monitoring (SCMo) are predictive maintenance systems that predict potential device failures and augment maintenance decisions, allowing for timely and efficient interventions. Despite the growing proliferation of such systems, prescriptive knowledge encompassing technical, business, and organizational aspects on how to design, develop, and deploy them in actual operational environments remains limited. To address this shortcoming of evidence-based design principles in practice, our action design research developed a predictive maintenance system that predicts SCMo device failures and augments the maintenance decisions about those devices. By doing so, we outline generalizable design principles to guide prospective predictive maintenance systems in SCMo. Collapse

Topics: artificial intelligence predictive maintenance organizational context decision making systems evaluation

Methods: machine learning design principle design artifact artificial neural network random forest classification

Theories: evidence-based design

Quantifying disease-interactions through co-occurrence matrices to predict early onset colorectal cancer

2023 | Decision Support Systems | Citations: 0

Authors: Kalgotra, Pankush; Sharda, Ramesh; Parasa, Sravanthi

Abstract: Colorectal cancer (CRC) is the third most common cancer in terms of the number o ... Expand

Abstract: Colorectal cancer (CRC) is the third most common cancer in terms of the number of cases and deaths in men and women in the USA. According to the Centers for Disease Control and Prevention, the CRC screening compliance rate remains low in the United States. It is even more concerning that the number of cases and deaths due to CRC is increasing in the younger population, for which there is no guideline to get colonoscopy screening. In this paper, we develop a novel network-based model to identify patients under 50 years of age having a high risk of CRC, particularly those who do not have a family history. Our model can help predict which patients are at risk of developing colorectal cancer to aid the practicing primary care physician and gastroenterologist to triage pa­ tients into meaningful risk groups to provide accelerated diagnostic steps and care to these patients. The model uses our proposed variables created through comorbidity network matrices obtained from CRC and non-CRC patients as inputs. We used the electronic medical records of thousands of CRC and non-CRC patients to develop and validate the models. Our model for younger patients correctly predicted 73.2% of the patients with future diagnoses with an area under the ROC curve of 0.81. At the 50% sensitivity, the false positive rate was 11.5%. The performance of our model is the highest in the current state-of-the-art. Our proposed variables quantifying the interactions between multiple diseases can also be adapted in future predictions of other diseases in a patient. Collapse

Topics: electronic health record database system data warehouse digital innovation decision support system

Methods: machine learning XGBoost computational algorithm gradient boosting descriptive statistic

Customer Complaints Response Priority Recommendation Engine: A HYBRID NLP Model

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Marshan, Alaa; Joshi, Nikhil; Ioannou, Athina; Spanaki, Konstantina

Abstract: The Consumer Financial Protection Bureau (CFPB) receives and processes consumer ... Expand

Abstract: The Consumer Financial Protection Bureau (CFPB) receives and processes consumer complaints about various financial services. Every complaint provides insight into problems that consumers experience. With an increasing number of CFPB complaints, manual prioritisation of these complaints is not feasible. This paper proposes a smart approach based on latent Dirichlet allocation (LDA) and Emotion detection to analyse the CFPB consumer complaints, extracting latent topics and emotions from CFPB complaints and assigning priority based on a predefined priority matrix. The automated priority recommendation engine provides faster and optimum prioritisation. The use of emotion detection and LDA allows categorization of complaints using two distinct aspects, topic, and emotion, providing varied priorities for the complaints. The average weighted priority calculation based on topics and emotions allows the recommendation engine to remove the dependence of prioritisation systems on user-selected labels. The proposed approach allows a configurable matrix, making the system implementation easy to configure as per business requirements. Collapse

Topics: Python missing data recommender system customer satisfaction website

Methods: topic model Cross-Industry Standard Process for Data Mining latent dirichlet allocation natural language processing cluster analysis

Punctuality Predictions in Public Transportation: Quantifying the Effect of External Factors

2023 | International Conference on Business Informatics | Citations: 0

Authors: Meyer-Hollatz, Tim; Schwarz, Nina; Werner, Tim

Abstract: Increasing availability of large-scale datasets for automatic vehicle location ... Expand

Abstract: Increasing availability of large-scale datasets for automatic vehicle location (AVL) in public transportation (PT) encouraged researchers to investigate data-driven punctuality prediction models (PPMs). PPMs promise to accelerate the mobility transition through more accurate prediction delays, increased customer service levels, and more efficient and forward-looking planning by mobility providers. While several PPMs show promising results for buses and longdistance trains, a comprehensive study on external factors' effect on tram services is missing. Therefore, we implement four machine learning (ML) models to predict departure delays and elaborate on the performance increase by adding realworld weather and holiday data for three consecutive years. For our best model (XGBoost) the average MAE performance increased by 17.33 % compared to the average model performance when only trained on AVL data enriched by timetable characteristics. The results provide strong evidence that adding informationbearing features improve the forecast quality of PPMs. Collapse

Topics: decision making explainable artificial intelligence artificial intelligence

Methods: literature study XGBoost machine learning Cross-Industry Standard Process for Data Mining LightGBM