Human versus automated agents: how user preferences affect future mobility systems

2023 | European Conference On Information Systems | Citations: 0

Authors: Ahadi, Ramin; Taudien, Anna; Ketter, Wolfgang

Abstract: Along with rapid advancements in digital, and physical technologies, shared aut ... Expand

Abstract: Along with rapid advancements in digital, and physical technologies, shared autonomous electric vehicles are forecasted to gradually complement and replace traditional human-based mobility systems. Information systems play a key role in such a deep socio-technical system to pave the path toward a more sustainable future. This study investigates a hybrid ride-hailing platform of automated and human-driven vehicles. Our focus lies on the demand side where we evaluate the influence of user behaviors on economic and environmental system performance. For this, we employ a data-driven agent-based simulation modeling heterogeneous vehicle and user agents calibrated by rental data of a leading vehicle-sharing company. Our findings declare that diverse customer responses to the introduction of shared autonomous electric vehicles yield significantly differing fleet performance and ecological costs. We also observe that the status quo customer communication design of ride-hailing platforms needs adjustments to maximize the potentials of future hybrid shared mobility systems. Collapse

Topics: ride sharing platform user behavior service quality decision making artificial intelligence

Methods: simulation agent based simulation experiment literature study sensitivity analysis

Theories: technology acceptance model general systems theory

Employing Machine Learning to Advance Agent-based Modeling in Information Systems Research

2023 | International Conference on Information Systems | Citations: 0

Authors: Bashardoust, Amirsiavosh; Safaei, Negin; Haki, Kazem; Shrestha, Yash Raj

Abstract: ... Expand

Abstract: Collapse

Topics: sensemaking Python organizational context innovation management business-to-business

Methods: sensitivity analysis theory development simulation robustness check artificial neural network

Theories: sociotechnical systems theory

CONFIDENCE MATTERS: A SIMULATION-BASED STABILITY ANALYSIS OF ALGORITHMIC STABLECOINS

2023 | European Conference On Information Systems | Citations: 0

Authors: Baumeister, Alexander; Hägele, Sascha

Abstract: ... Expand

Abstract: Collapse

Topics: stablecoin Ethereum cryptocurrency

Methods: simulation Monte Carlo simulation agent based simulation

Interorganizational Information System Deployment in Supply Chain Triads

2023 | International Conference on Information Systems | Citations: 0

Authors: Bodendorf, Frank; Schmidt, Lars; Franke, Jörg

Abstract: Interorganizational information systems (IOIS) are valuable tools providing pla ... Expand

Abstract: Interorganizational information systems (IOIS) are valuable tools providing platforms for information flow enabling more efficient and reliable collaboration in digitalized supply chains. An IOIS is subject to influencing factors originating in the company and environment. Inspired by complex adaptive system theory, an agent-based simulation model is designed, exploring factors affecting the integration and efficiency of IOIS. These factors are derived from resource-based view and dynamic capabilities theory. The influence on information system deployment is assessed by merging these factors into exogenous, intercompany climate, and operational dimensions. First, the results indicate that product-specific factors have a greater influence than the environment when deploying an IOIS. Second, deliberate design of IC relationships should be considered during the development of an IOIS. Third, extensive information exchange between supply chain partners might be disadvantageous for IOIS utilization. Fourth, the advantages of IOIS can be lost when completely open systems are used. Collapse

Topics: supply chain management information exchange value creation computer hardware personal computer

Methods: experiment simulation regression analysis method linear regression analysis nonlinear regression analysis

Theories: complex adaptive system

Introduction to the Minitrack on Personal and Population Health Technologies in Disease Surveillance

2023 | HICSS | Citations: 0

Authors: Goldfine, Charlotte; Chai, Peter R.; Lai, Jeffrey; Carreiro, Stephanie

Abstract: Recent advances in wearable, implantable and ingestible technologies permit unp ... Expand

Abstract: Recent advances in wearable, implantable and ingestible technologies permit unprecedented assessments of various aspects of health and wellness. The ubiquity of smartphones, smart watches and fitness tracking tools has provided vast amounts of digital physiologic and behavioral data. These "phenotypes" of health -prosody of smartphone use, biometric data surrounding health events, geolocation and ambient environment conditions -provide an opportunity for social scientists, engineers and clinicians to advance health interventions antecedent to exacerbations of disease. For example, phenotypes of smartphone use have been correlated with changes in mental health and pain, ingestible sensors measure real-time changes and contexts of medication adherence in various diseases, and biometric data may predict different states of health conditions prior to their clinically apparent manifestation.The COVID-19 pandemic continues to spur increasing acceptance of digital biomarkers and personal technologies as health management tools. Additionally, technologies that leverage public health infrastructure such as wastewater-based epidemiology and crowdsourced street maps provide novel insights into the effects of disease in communities at the population health level.The goal of this minitrack is to facilitate multidisciplinary collaboration and exploration of various facets of health technologies and their ability to surveil and predict disease. Last year's minitrack explored the design and implementation challenges as innovative technologies were deployed in clinical settings: virtual windows to enhance the patient experience in the emergency department, wearable sensors to detect alcohol consumption, agent-based modeling to evaluate the cost-savings of poison control centers, and the use of noise-cancelling earbuds to improve sleep quality for healthcare shift workers.This year's minitrack features four papers that explore innovative technological applications to improve the treatment and detection of disease states.In our first paper, the authors present a novel augmented reality (AR) training for two emergency medical procedures (bag-valve-mask ventilation and needle decompression of pneumothorax), demonstrating no difference between AR and standard video training in usability and usefulness scores or expert rating of the technique. Our second paper details the development of a novel asynchronous learning module for medical toxicology education that can uniquely be delivered via text-messaging, an intervention that emergency medicine residents and physician assistants at various stages of training find to be easy-to-use and of high educational value. The third paper presents formative qualitative work toward the development of a gamified app to help individuals in Vietnam maintain adherence to antituberculosis therapy. Our fourth paper examines the use of a wearable sensor system to detect stress and craving in individuals with substance use disorder. Finally, we conclude with a discussion regarding the ability to leverage technology to detect and prevent abuse in academic medicine.We are excited to re-convene in person this year at HICSS-56. We are looking forward to generating fruitful discussions of the featured papers and fostering the development of new ideas for future work. Collapse

Topics: smart wearable device mobile application online chat usability smart device

Methods: wearables based research literature sample agent based simulation

A Longitudinal Examination of AI Fairness on Online Labor Markets

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Green, Brittany; Ahuja, Manju; Sundrup, Rui

Abstract: ... Expand

Abstract: Collapse

Topics: artificial intelligence IT career online labor market software developer electronic market

Methods: agent based simulation simulation longitudinal research experiment regression analysis method

Theories: organizational justice theory contingency theory

A Longitudinal Examination of AI Fairness on Online Labor Markets

2023 | International Conference on Business Informatics | Citations: 0

Authors: Green, Brittany; Ahuja, Manju; Sundrup, Rui; Quinn, Ryan

Abstract: While online labor markets (OLMs) provide many benefits including flexibility a ... Expand

Abstract: While online labor markets (OLMs) provide many benefits including flexibility and data driven AI matching systems, gender and other social biases have been shown in OLMs, and research demonstrates AI can also perpetuate bias. However, previous OLM research assumes bias is static over time and independent of the AI algorithm. To help design OLMs that minimize the detrimental impact of biases on marginalized social groups, we investigate the interaction among individual characteristics and AI sources of biases over the long-term and evaluate auditing strategies using an agent-based simulation model. We also empirically investigate hiring bias using a cross section of data from a popular online labor market, and we use this data to inform our simulation. We then plan to develop and empirically test a framework to evaluate AI fairness and the interaction of different biases on OLMs and test an audit strategy to mitigate biases. We plan to extend the literature on OLMs by integrating fairness and intersectionality research to evaluate the impact of biases. Collapse

Topics: artificial intelligence online labor market IT career task characteristic individual characteristic

Methods: simulation longitudinal research agent based simulation Student's t-test experiment

Theories: contingency theory organizational justice theory

Fraud Detection in Mobile Payment Systems using an XGBoost-based Framework

2023 | Information Systems Frontiers | Citations: 0

Authors: Hajek, Petr; Abedin, Mohammad Zoynul; Sivarajah, Uthayasankar

Abstract: Mobile payment systems are becoming more popular due to the increase in the numb ... Expand

Abstract: Mobile payment systems are becoming more popular due to the increase in the number of smartphones, which, in turn, attracts the interest of fraudsters. Extant research has therefore developed various fraud detection methods using supervised machine learning. However, sufficient labeled data are rarely available and their detection performance is negatively affected by the extreme class imbalance in financial fraud data. The purpose of this study is to propose an XGBoost-based fraud detection framework while considering the financial consequences of fraud detection systems. The framework was empirically validated on a large dataset of more than 6 million mobile transactions. To demonstrate the effectiveness of the proposed framework, we conducted a comparative evaluation of existing machine learning methods designed for modeling imbalanced data and outlier detection. The results suggest that in terms of standard classification measures, the proposed semi-supervised ensemble model integrating multiple unsupervised outlier detection algorithms and an XGBoost classifier achieves the best results, while the highest cost savings can be achieved by combining random under-sampling and XGBoost methods. This study has therefore financial implications for organizations to make appropriate decisions regarding the implementation of effective fraud detection systems. Collapse

Topics: fraud detection mobile system mobile payment electronic payment Python

Methods: XGBoost machine learning anomaly detection supervised learning experiment

The Impact of Human-Artificial Intelligence Partnerships on Organizational Learning

2023 | European Conference On Information Systems | Citations: 0

Authors: Hendriks, Patrick; Sturm, Timo; Olt, Christian; Buxmann, Peter

Abstract: To make sense of their increasingly digital and complex environments, organizat ... Expand

Abstract: To make sense of their increasingly digital and complex environments, organizations strive for a future in which machine learning (ML) systems join humans in collaborative learning partnerships to complement each other's learning capabilities. While these so-called artificial assistants enable their human partners (and vice versa) to gain insights about unique knowledge domains that would otherwise remain hidden from them, they may also disrupt and impede each other's learning. To explore the virtuous and vicious dynamics that affect organizational learning, we conduct a series of agent-based simulations of different learning modes between humans and artificial assistants in an organization. We find that aligning the learning of humans and artificial assistants and allowing them to influence each other's learning processes equally leads to the highest organizational performance. Collapse

Topics: organization learning organizational memory knowledge base human AI collaboration artificial intelligence

Methods: simulation agent based simulation

Theories: theory of bounded rationality

How to design platform ecosystems by intrapreneurs: Implications from action design research on IoT-based platform

2023 | Electronic Markets | Citations: 0

Authors: Inoue, Yuki; Takenaka, Takeshi; Kasasaku, Takami; Tamegai, Tadafumi; Arai, Ryohei

Abstract: The recent technological evolution of the Internet of Things (IoT) and data scie ... Expand

Abstract: The recent technological evolution of the Internet of Things (IoT) and data sciences has created opportunities for intrapreneurs in non-platform firms to expand their businesses into platform ecosystem-related businesses. However, previous studies have typically focused on cases involving entrepreneurs. This study aims to clarify how intrapreneurs’ design for platform ecosystems could be different from that of entrepreneurs. We conducted an action design research (ADR) project in collaboration with a company for 29 months, and designed a platform ecosystem structure based on technological platforms related to radio frequency identifiers (RFID). Our main contribution is the following six-step process that describes how intrapreneurs design platform ecosystems: (1) designing an initial ecosystem structure based on platform ecosystem concepts and certain concepts related to the targeted market; (2) analyzing past business cases; (3) making the ecosystem structure into concrete shape; (4) verifying its validity; (5) elaborating the ecosystem structure; and (6) proposing the designed ecosystem business. Our findings highlight the differences between intrapreneurs’ and entrepreneurs’ designs of the ecosystem. First, when the design processes are underway, the direction of the design of the ecosystem needs to be flexibly modified to align with the strategy of the firm. Second, evidence for the success of the proposed platform ecosystem is required to reduce uncertainty and clarify the legitimacy of the proposition. Third, the structure of a platform ecosystem designed by intrapreneurs becomes a style that supports the existing businesses and networks of the firm. Collapse

Topics: digital ecosystem radio frequency identification digital service logistics management price management

Methods: survey simulation data transformation design process action design research