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

Using Isolation Forest and Alternative Data Products to Overcome Ground Truth Data Scarcity for Improved Deep Learning-based Agricultural Land Use Classification Models

2023 | HICSS | Citations: 0

Authors: García Pereira, Agustín; Porwol, Lukasz; Ojo, Adegboyega

Abstract: High-quality labelled datasets represent a cornerstone in the development of dee ... Expand

Abstract: High-quality labelled datasets represent a cornerstone in the development of deep learning models for land use classification. The high cost of data collection, the inherent errors introduced during data mapping efforts, the lack of local knowledge, and the spatial variability of the data hinder the development of accurate and spatially-transferable deep learning models in the context of agriculture. In this paper, we investigate the use of Isolation Forest (IF), an anomaly detection algorithm, to reduce noise in a large-scale, low-resolution alternative ground truth dataset used to train land use deep learning models. We use a modest-size, high-resolution and high-fidelity manually collected ground-truth dataset to calibrate Isolation Forest parameters and evaluate our approach, highlighting the relatively low cost of the methodology. Our data-centric methodology demonstrates the efficacy of deep learning methods coupled with IF to create mid-resolution land-use models and map products for agriculture using an alternative ground-truth dataset. Moreover, we compare our deep learning approach with a traditional algorithm used in remote sensing and evaluate the spatial transferability of the created models. Finally, we reflect upon the lessons learnt and future work. Collapse

Topics: cloud computing Python programming language open source geographic information system

Methods: experiment deep learning computational algorithm isolation forest random forest classification

Individual Differences and Situational Constraint Predict Information Search in Negotiation Planning

2023 | Group Decision and Negotiation | Citations: 0

Authors: Le, Dai Quy; Jang, Daisung

Abstract: Planning is critical for negotiation success as it facilitates obtaining superio ... Expand

Abstract: Planning is critical for negotiation success as it facilitates obtaining superior outcomes. However, little empirically is known about this topic. We argue that individual differences are important to understanding planning behavior because planning affords greater opportunities for individual differences to manifest compared to other phases of negotiation. We conducted a series of studies with the aim of understanding how the Big Five factors and gender predict information search and preference while planning. In Study 1, we examined information search behavior using the Mouselab paradigm. When the search space was large, agreeableness predicted persistence in search, and women spent significantly more time on the task, and looked for value creating and relationship related information to a greater extent than men (Study 1a). In a more constrained situation or with a smaller search space, few associations between individual differences and search behavior emerged (Studies 1b and 1c). In Study 2, we used a survey design to elicit preferences for information type. In this task, multiple personality factors predicted preferences. Conscientiousness and openness predicted preferences for value claiming information, and women preferred value creating information. Conscientiousness predicted preference for value claiming choice of information through the preference for value claiming information. How individual differences manifest in information search and preference in negotiation planning is a function of both task type and complexity. Collapse

Topics: personality information storage and retrieval system decision making

Methods: survey design survey statistical hypothesis test descriptive statistic Poisson regression

Theories: big five model role theory

To Differentiate Or Not To Differentiate? The Role of Product Characteristics in the Sharing Economy

2022 | European Conference On Information Systems | Citations: 0

Authors: Demircan, Muhammed; Schroer, Karsten; Fritze, Martin Paul; Ketter, Wolfgang

Abstract: An important ambiguity in the sharing economy literature concerns the role of p ... Expand

Abstract: An important ambiguity in the sharing economy literature concerns the role of product variety. Do physical product characteristics provide scope for differentiation in a sharing economy context, and if so, under which circumstances? Resolving this ambiguity is important as it can have large operational and strategic implications for sharing economy businesses. We use discrete choice modeling on a unique carsharing dataset and behavioral online experiments to study how users select between product options of varying quality and brand in a shared consumption context. We find that, in general, there is a trend towards utilitarian access-based consumption in which product characteristics and product brand matter less. However, we observe that hedonistic use cases tend to shift preferences significantly toward more premium products. Our results highlight the need for a more nuanced consideration of product differentiation in sharing economy research. Collapse

Topics: sharing platform ride sharing platform product differentiation application programming interface mobile application

Methods: experiment conjoint analysis analysis of covariance quasi experiment qualitativ observational study

Theories: theory of affordance

When Do Firms Trade Patents?

2022 | Organization Science | Citations: 0

Authors: Kwon, Jung H.; Park, Haemin Dennis; Deng, Shu

Abstract: Drawing on the Coase theorem, we consider a firm’s decision to transfer patent o ... Expand

Abstract: Drawing on the Coase theorem, we consider a firm’s decision to transfer patent ownership to another firm in the markets for innovation. We deem that the proximity of a patent’s technology structure to that of a firm’s patent portfolio will generally result in greater marginal productivity of the patent, leading to enhanced prospects for the firm’s economic return. We thus predict that firms are more likely to trade patents when the technology structure of a patent is closer to the technology stock of a potential buyer compared with that of its original assignee. However, such a relationship will be weaker when a potential buyer and the original assignee have greater product-market overlap or when the assignee has superior technological capability. We test these predictions by employing a dyad-level analysis of transactional decisions during the 1987–2016 period on 40,110 U.S. patents assigned to 57 major biopharmaceutical firms. Our study provides novel insights on factors that facilitate or inhibit patent trade in the markets for innovation. Collapse

Topics: database system innovation management research and development strategic management logistics management

Methods: regression analysis method robustness check proportional hazards model Compustat survival analysis

Theories: transaction cost economics

Addiction to Social Networking Sites and User Responses: Toward A Typological Theory and its Relation to Users' Personality Traits

2022 | ACM SIGMIS Database | Citations: 0

Authors: Qahri-Saremi, Hamed; Vaghefi, Isaac; Turel, Ofir

Abstract: Prior studies have primarily used "variable-centered" perspectives to identify f ... Expand

Abstract: Prior studies have primarily used "variable-centered" perspectives to identify factors underlying user responses to social networking site (SNS) addiction, their predictors and outcomes. This paper extends this perspective by taking a person-centered approach to examine (1) the prototypical subpopulations (profiles) of users' extent of SNS addiction and responses to it, (2) how affiliations with these profiles can explain user behaviors toward SNS use, and (3) how personality traits can predict affiliations with these profiles. To this end, we propose a typological theory of SNS addiction and user responses to it via two empirical, personcentered studies. Study 1 draws on survey data from 188 SNS users to develop a typology of users based on the extent of their SNS addiction and their responses to it. It further examines the relations between affiliation with these profiles and users' SNS discontinuance intention, as a typical behavioral response to SNS addiction. Study 2 uses survey data from 284 SNS users to validate the user typology developed in Study 1 and investigate its relations to users' Big Five personality traits. Our findings shed light on a typology of five prototypical profiles of SNS users-cautious, regular, consonant, dissonant, and hooked-who differ in their extent of SNS addiction and their cognitive, emotional, and behavioral responses to it. Our findings also demonstrate how Big Five personality traits can predict user affiliations with these prototypical profiles. Collapse

Topics: personality self efficacy smartphone information technology addiction WeChat

Methods: survey SEM tool cross sectional research chi squared test self reported survey

Theories: big five model cognitive dissonance theory dual-system theory

DSSAE: Deep Stacked Sparse Autoencoder Analytical Model for COVID-19 Diagnosis by Fractional Fourier Entropy

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

Authors: Wang, Shui-Hua; Zhang, Xin; Zhang, Yu-Dong

Abstract: (Aim) COVID-19 has caused more than 2.28 million deaths till 4/Feb/2021 while it ... Expand

Abstract: (Aim) COVID-19 has caused more than 2.28 million deaths till 4/Feb/2021 while it is still spreading across the world. This study proposed a novel artificial intelligence model to diagnose COVID-19 based on chest CT images. (Methods) First, the two-dimensional fractional Fourier entropy was used to extract features. Second, a custom deep stacked sparse autoencoder (DSSAE) model was created to serve as the classifier. Third, an improved multiple-way data augmentation was proposed to resist overfitting. (Results) Our DSSAE model obtains a micro-averaged F1 score of 92.32% in handling a four-class problem (COVID-19, community-acquired pneumonia, secondary pulmonary tuberculosis, and healthy control). (Conclusion) Our method outperforms 10 state-of-the-art approaches. Collapse

Topics: artificial intelligence web service

Methods: machine learning computational algorithm deep learning autoencoder data transformation

Sustainability vs. Price: Analysis of Electric Multi-Modal Vehicle Sharing Systems under Substitution Effects

2022 | European Conference On Information Systems | Citations: 0

Authors: Demircan, Muhammed; Ahadi, Ramin; Ketter, Wolfgang

Abstract: To pave the path for sustainable mobility, Information Systems are a promising ... Expand

Abstract: To pave the path for sustainable mobility, Information Systems are a promising tool to encourage users to adopt more sustainable mobility behavior. In this study, we investigate how potential demand management interventions affect the economic and environmental metrics of a multi-modal vehicle sharing operator. To this end, we narrow our focus on two important user characteristics, namely the users' flexibility and willingness to pay an additional premium for more environmentally sustainable vehicles. Our study employs a combined discrete-event and multi-agent simulation approach, which we calibrate with realworld rental data of leading free-floating vehicle sharing platforms. The results show that it is economically and ecologically disadvantageous for both the society and the fleet operator to simply increase users' mode choice flexibility. However, we clearly observe that this picture flips once users are willing to pay a surcharge to rent more environmentally sustainable vehicles. Collapse

Topics: green IS willingness to pay application programming interface service quality sharing platform

Methods: simulation multinomial logistic regression agent based simulation regression analysis method Monte Carlo simulation

Theories: socio technical theory

Algorithmic Transparency and Contact-tracing Apps – An Empirical Investigation

2021 | Americas Conference on Information Systems | Citations: 0

Authors: Bitzer, Tobias; Wiener, Martin; Morana, Stefan

Abstract: Contact-tracing apps are considered one of the core information technologies to ... Expand

Abstract: Contact-tracing apps are considered one of the core information technologies to help contain the spread of the COVID-19 pandemic. However, they need to be adopted broadly to be effective. In this study, we apply the concept of algorithmic transparency (AT) to contact-tracing apps and hypothesize that users prefer apps with a high level of disclosure of information about the app's inner workings (referred to as transformation AT) and that disclosure increases user comprehension and trust. We empirically validate our hypotheses through an online experiment with 116 participants. We find that the level of transformation AT of a contact-tracing app is positively related to users' adoption behavior, comprehension, and trust. Collapse

Topics: mobile application contact tracing mobile application technology adoption mobile system user acceptance

Methods: experiment computational algorithm statistical hypothesis test descriptive statistic linear regression analysis

Exploiting the Temporal Dimension of Remotely Sensed Imagery with Deep Learning Models

2021 | HICSS | Citations: 0

Authors: García Pereira, Agustín; Porwol, Lukasz; Ojo, Adegboyega; Curry, Edward

Abstract: The rapid rise of artificial intelligence and the increasing availability of ope ... Expand

Abstract: The rapid rise of artificial intelligence and the increasing availability of open Earth Observation (EO) data present new opportunities to address important global problems such as the proliferation of agricultural systems which endanger ecological sustainability. Despite the plethora of satellite images describing a given location on earth every year, very few deep learning-based solutions have harnessed the temporal and sequential dynamics of land use to map agricultural practices. This paper compares different approaches to classify agricultural land use exploiting the temporal and spectral dimensions of EO data. The results show greater efficiency of the presented deep learning-based algorithms compared to state-of-theart approaches when mapping agricultural classes. Collapse

Topics: cloud computing artificial intelligence

Methods: computational algorithm experiment random forest classification data transformation dimensionality reduction