Introduction to the Minitrack on Explainable Artificial Intelligence (XAI)

2023 | HICSS | Citations: 0

Authors: Abedin, B.; Meske, C.; Rabhi, F.; Klier, M.

Abstract: Artificial Intelligence (AI) already reached or even surpassed the task perform ... Expand

Abstract: Artificial Intelligence (AI) already reached or even surpassed the task performance of humans in various domains. However, most AI systems are still "black boxes" that are difficult to comprehend -not only for developers, but also for users and decision-makers. Explainable Artificial Intelligence (XAI) is aimed at intelligent systems that are highly performant to enable their users to understand, appropriately trust, and scrutinize them. Collapse

Topics: explainable artificial intelligence artificial intelligence

Methods: experiment structured literature research

Explaining Explainable Artificial Intelligence: An integrative model of objective and subjective influences on XAI

2023 | HICSS | Citations: 0

Authors: Alarcon, G.; Willis, S.

Abstract: Explainable artificial intelligence (XAI) is a new field within artificial inte ... Expand

Abstract: Explainable artificial intelligence (XAI) is a new field within artificial intelligence (AI) and machine learning (ML). XAI offers transparency of AI and ML that can bridge the gap in information that has been absent from "black-box" models. Given its nascency, there are several taxonomies of XAI in the literature. The current paper incorporates the taxonomies in the literature into one unifying framework, which defines the types of explanations, types of transparency, and model methods that together inform the user's processes towards developing trust in AI and ML systems. Collapse

Topics: artificial intelligence explainable artificial intelligence usability human computer interaction

Methods: computational algorithm theory development artificial neural network

Counterfactual Explanations for Incorrect Predictions Made by AI Models

2023 | International Conference on Information Systems | Citations: 0

Authors: Asrzad, Amir; Li, Xiaobai

Abstract: Advanced AI models are powerful in making accurate predictions for complex prob ... Expand

Abstract: Advanced AI models are powerful in making accurate predictions for complex problems. However, these models often operate as black boxes. This lack of interpretability poses significant challenges, especially in high-stakes applications such as finance, healthcare, and criminal justice. Explainable AI seeks to address the challenges by developing methods that can provide meaningful explanations for humans to understand. When black box models are used for prediction, they inevitably produce errors. It is important to appropriately explain incorrect predictions. This problem, however, has not been addressed in the literature. In this study, we propose a novel method to provide explanations for misclassified cases made by black box models. The proposed method takes a counterfactual explanation approach. It builds a decision tree to find the best counterfactual examples for explanations. Incorrect predictions are rectified using a trust score measure. We validate the proposed method in an evaluation study using real-world data. Collapse

Topics: artificial intelligence explainable artificial intelligence local interpretable model agnostic explanation decision making enterprise information system

Methods: machine learning decision tree classification literature study random forest classification experiment

Give me 3W1H: A Bibliometric View on Accountable AI

2023 | International Conference on Information Systems | Citations: 0

Authors: Bartsch, Sebastian; Schmidt, Jan-Hendrik

Abstract: Accountability is crucial to make stakeholders of Artificial Intelligence (AI)- ... Expand

Abstract: Accountability is crucial to make stakeholders of Artificial Intelligence (AI)-based systems justify their actions, thereby explaining the harm such systems cause to AI users. Due to the importance of accountability in the context of AI, accountability was introduced into IS research through literature reviews. Therefore, while IS research's understanding of accountability covers the necessary depth, it comes at the expense of its essential breadth. Using a bibliometric analysis with 19,978 English-language papers, we shed light on the essential breadth posing three W-and one H-questions (When, What, Whereof, and How). Therefore, we contribute to IS research by highlighting the urgent need to revise existing definitions of accountability in the context of AI and establish them in IS research. We argue that a missing revision leads to non-transferrable findings within IS research. Accordingly, this study serves as a starting point for adapting definitions and creating a shared understanding in IS research. Collapse

Topics: artificial intelligence explainable artificial intelligence legal context database system IT security

Methods: word embedding word2vec bibliometric analysis machine learning supervised learning

Expl(AI)ned: The Impact of Explainable Artificial Intelligence on Users’ Information Processing

2023 | Information Systems Research | Citations: 0

Authors: Bauer, Kevin; von Zahn, Moritz; Hinz, Oliver

Abstract: Because of a growing number of initiatives and regulations, predictions of moder ... Expand

Abstract: Because of a growing number of initiatives and regulations, predictions of modern artificial intelligence (AI) systems increasingly come with explanations about why they behave the way they do. In this paper, we explore the impact of feature-based explanations on users’ information processing. We designed two complementary empirical studies where participants either made incentivized decisions on their own, with the aid of opaque predictions, or with explained predictions. In Study 1, laypeople engaged in the deliberately abstract investment game task. In Study 2, experts from the real estate industry estimated listing prices for real German apartments. Our results indicate that the provision of feature-based explanations paves the way for AI systems to reshape users’ sense making of information and understanding of the world around them. Specifically, explanations change users’ situational weighting of available information and evoke mental model adjustments. Crucially, mental model adjustments are subject to the confirmation bias so that misconceptions can persist and even accumulate, possibly leading to suboptimal or biased decisions. Additionally, mental model adjustments create spillover effects that alter user behavior in related yet disparate domains. Overall, this paper provides important insights into potential downstream consequences of the broad employment of modern explainable AI methods. In particular, side effects of mental model adjustments present a potential risk of manipulating user behavior, promoting discriminatory inclinations, and increasing noise in decision making. Our findings may inform the refinement of current efforts of companies building AI systems and regulators that aim to mitigate problems associated with the black-box nature of many modern AI systems. History: Alessandro Acquisti, senior editor; Jason Chan, associate editor. Funding: This work was supported by the Deutsche Forschungsgemeinschaft (DFG) (Projek 449023539), Volkswagen Foundation (ML2MT), and LeibnizInstitute for Financial Research SAFE. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2023.1199. Collapse

Topics: explainable artificial intelligence artificial intelligence shapley additive explanation local interpretable model agnostic explanation decision making

Methods: F-test regression analysis method experiment field study robustness check

AI-Enhanced Hybrid Decision Management

2023 | Business & Information Systems Engineering | Citations: 0

Authors: Bork, Dominik; Ali, Syed Juned; Dinev, Georgi Milenov

Abstract: The Decision Model and Notation (DMN) modeling language allows the precise speci ... Expand

Abstract: The Decision Model and Notation (DMN) modeling language allows the precise specification of business decisions and business rules. DMN is readily understandable by business users involved in decision management. However, as the models get complex, the cognitive abilities of humans threaten manual maintainability and comprehensibility. Proper design of the decision logic thus requires comprehensive automated analysis of e.g., all possible cases the decision shall cover; correlations between inputs and outputs; and the importance of inputs for deriving the output. In the paper, the authors explore the mutual benefits of combining human-driven DMN decision modeling with the computational power of Artificial Intelligence for DMN model analysis and improved comprehension. The authors propose a model-driven approach that uses DMN models to generate Machine Learning (ML) training data and show, how the trained ML models can inform human decision modelers by means of superimposing the feature importance within the original DMN models. An evaluation with multiple real DMN models from an insurance company evaluates the feasibility and the utility of the approach. Collapse

Topics: artificial intelligence explainable artificial intelligence perceived usefulness price management extensible markup language

Methods: computational algorithm decision tree classification experiment conceptual modelling simulation

Analyzing Patients’ EHR: Predicting and Explaining Admission Consequences for COPD and Liver Disease Patients

2023 | International Conference on Information Systems | Citations: 0

Authors: Ben-Assuli, Ofir; Geva, Gaya

Abstract: This study analyzed the admission outcomes in chronic patients (with COPD, and ... Expand

Abstract: This study analyzed the admission outcomes in chronic patients (with COPD, and Liver disease) to demonstrate the feasibility of applying prediction methods on EHR records while incorporating an explainable AI technique. We predicted three target variables: 30-day readmission, Medium&Long Length of Stay and Single-day admission and analyzed the features using an explainable AI technique, the SHapley Additive exPlanations (SHAP). The results show that Readmission had higher prediction scores than all other dependent variables. Some features affected all target variables with either positive or negative influence including: Age, Charlson comorbidity index, Day-Shift, Gender, using EHR screens and Insurance cover level. These findings thus point to the value of using Machine-Learning combined with an explainable AI method to understand and assess the risks factors. The assessment of the potential factors leading to multiple complications can bolster prevention-oriented medical decisions to groups of patients but can also be tailored to the patient level. Collapse

Topics: shapley additive explanation explainable artificial intelligence Python IT work artificial intelligence

Methods: machine learning XGBoost logistic regression artificial neural network classification method

Explainable artificial intelligence in information systems: A review of the status quo and future research directions

2023 | Electronic Markets | Citations: 4

Authors: Brasse, Julia; Broder, Hanna Rebecca; Förster, Maximilian; Klier, Mathias; Sigler, Irina

Abstract: The quest to open black box artificial intelligence (AI) systems evolved into an ... Expand

Abstract: The quest to open black box artificial intelligence (AI) systems evolved into an emerging phenomenon of global interest for academia, business, and society and brought about the rise of the research field of explainable artificial intelligence (XAI). With its pluralistic view, information systems (IS) research is predestined to contribute to this emerging field; thus, it is not surprising that the number of publications on XAI has been rising significantly in IS research. This paper aims to provide a comprehensive overview of XAI research in IS in general and electronic markets in particular using a structured literature review. Based on a literature search resulting in 180 research papers, this work provides an overview of the most receptive outlets, the development of the academic discussion, and the most relevant underlying concepts and methodologies. Furthermore, eight research areas with varying maturity in electronic markets are carved out. Finally, directions for a research agenda of XAI in IS are presented. Collapse

Topics: explainable artificial intelligence artificial intelligence user requirement electronic market user experience

Methods: literature study literature sample cluster analysis synthesis machine learning

Theories: information systems theory activity theory agency theory attribution theory cognitive fit theory

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

Conducting Design Science Research in Society 5.0 – Proposal of an Explainable Artificial Intelligence Research Methodology

2023 | DESRIST | Citations: 0

Authors: Daase, Christian; Turowski, Klaus

Abstract: Every technological or scientific advance is accompanied by a change in social s ... Expand

Abstract: Every technological or scientific advance is accompanied by a change in social structures, moral concepts, laws and education. As more and more people gain access to the digital world and the technical possibilities increase at the same rate, the excitement to carry out computer-based engineering projects increases. This in turn leads to an elevated demand for appropriate design-oriented methodologies, especially from the field of design science research (DSR), which in a sense democratize digital engineering. The idea of Society 5.0 is one of the major shifts in perspective on the role of technology, humans and their interaction in a shared living world. As a core component, artificial intelligence (AI), together with the Internet of things and big data analytics, is expected to have the most significant impact on the transformation toward smart societies. In this study, a systematic literature review of a total of 137 published articles addressing AI projects using DSR methodologies is conducted with the purpose of establishing a unified methodology for explainable AI-focused DSR projects. The proposed methodology further takes into account the particularities of AI at the varying advanced levels of artificial narrow intelligence (ANI) to the presumed necessities for approaching artificial general intelligence (AGI), which has not yet been fully realized. By allowing AI researchers to rely on a generalized methodological approach, the gap between behavioral science and design science is bridged, with the former laying the foundation for understanding living reality and the latter developing the means to mimic that reality as part of artificiality. Collapse

Topics: artificial intelligence explainable artificial intelligence database system artificial general intelligence

Methods: design science design methodology structured literature research literature sample