Results

Found 2 articles

Clear filters

Designing a feature selection method based on explainable artificial intelligence
PDF
2022 | Electronic Markets | Citations: 7
Authors: Zacharias, Jan; von Zahn, Moritz; Chen, Johannes; Hinz, Oliver

Abstract: Nowadays, artificial intelligence (AI) systems make predictions in numerous high ... Expand

Abstract: Nowadays, artificial intelligence (AI) systems make predictions in numerous high stakes domains, including credit-risk assessment and medical diagnostics. Consequently, AI systems increasingly affect humans, yet many state-of-the-art systems lack transparency and thus, deny the individual’s “right to explanation”. As a remedy, researchers and practitioners have developed explainable AI, which provides reasoning on how AI systems infer individual predictions. However, with recent legal initiatives demanding comprehensive explainability throughout the (development of an) AI system, we argue that the pre-processing stage has been unjustifiably neglected and should receive greater attention in current efforts to establish explainability. In this paper, we focus on introducing explainability to an integral part of the pre-processing stage: feature selection. Specifically, we build upon design science research to develop a design framework for explainable feature selection. We instantiate the design framework in a running software artifact and evaluate it in two focus group sessions. Our artifact helps organizations to persuasively justify feature selection to stakeholders and, thus, comply with upcoming AI legislation. We further provide researchers and practitioners with a design framework consisting of meta-requirements and design principles for explainable feature selection. Collapse

Semantic filters: exploratory data analysis confounding variable

Topics: shapley additive explanation explainable artificial intelligence artificial intelligence evaluation criteria ease of use

Methods: design principle design artifact design framework design science focus group
Email overload: Exploring the moderating role of the perception of email as a ‘business critical’ tool
PDF
2011 | International Journal of Information Management | Citations: 0
Authors: Sumecki, David; Chipulu, Maxwell; Ojiako, Udechukwu

Abstract: a b s t r a c tThe management of email remains a major challenge for organisati ... Expand

Abstract: a b s t r a c tThe management of email remains a major challenge for organisations. In this article, we explore the extent of the perceptions of email as a business critical tool within an organisation and how the level of such perceptions may moderate the level of email overload experienced by individuals within the organisation. Data from a sample of 1100 employees of a multinational technology firm are analysed using multivariate techniques. The results suggest that without a clearly stated code of email practice within an organisation, there are likely to be large variations in what is perceived as 'business-critical' email and, as a result, a substantial amount of email generated within the organisation may not be 'business-critical', potentially increasing the level of 'email-overload' experienced by individuals within the organisation. Collapse

Semantic filters: exploratory data analysis confounding variable

Topics: electronic mail missing data website organizational context organizational culture

Methods: survey regression analysis method logistic regression linear regression analysis computational algorithm

Page 1 of 1

AIS11

Journals

Conferences

Semantic Filter

Found 2 articles

Designing a feature selection method based on explainable artificial intelligence

Email overload: Exploring the moderating role of the perception of email as a ‘business critical’ tool