Search results

Checklist for evaluating the meaningfulness of AI system explanations for internal users

It is now widely accepted that decisions made by AI systems must be explainable to their users. However, in practice, it often remains unclear how this explainability should be concretely implemented. This is especially important for nontechnical users, such as claims assessors at insurance companies, who need to understand AI system decisions and be able to explain them to customers. Think, for example, of explaining a rejected insurance claim or loan application. Although the importance of explainable AI is broadly recognized, there is often a lack of practical tools to achieve it. That’s why, in this handbook, we have combined insights from two use cases in the financial sector with findings from an extensive literature review. This has led to the identification of 30 key aspects of meaningful AI explanations. Based on these aspects, we developed a checklist to help AI developers make their systems more explainable. The checklist not only provides insight into how understandable an AI application currently is for end users, but also highlights areas for improvement.

This is our music

To Meet, to Matter, and to Have Fun

Interventions for older people are often not evaluated and, if evaluated, are not proven successful. Based on a systematic literature review and two qualitative studies about the social needs of older people, an intervention has been developed, implemented, and evaluated. Important social needs that emerged from these studies are connectedness, meaningfulness, and independence.

Effects of major urban redesign on sedentary behavior, physical activity, active transport and health-related quality of life in adults

Background: The built environment is increasingly recognized as a determinant for health and health behaviors. Existing evidence regarding the relationship between environment and health (behaviors) is varying in significance and magnitude, and more high-quality longitudinal studies are needed. The aim of this study was to evaluate the effects of a major urban redesign project on physical activity (PA), sedentary behavior (SB), active transport (AT), health-related quality of life (HRQOL), social activities (SA) and meaningfulness, at 29–39 months after opening of the reconstructed area. Methods: PA and AT were measured using accelerometers and GPS loggers. HRQOL and sociodemographic characteristics were assessed using questionnaires. In total, 241 participants provided valid data at baseline and follow-up. We distinguished three groups, based on proximity to the intervention area: maximal exposure group, minimal exposure group and no exposure group. Results: Both the maximal and minimal exposure groups showed significantly different trends regarding transportbased PA levels compared to the no exposure group. In the exposure groups SB decreased, while it increased in the no exposure group. Also, transport-based light intensity PA remained stable in the exposure groups, while it significantly decreased in the no exposure group. No intervention effects were found for total daily PA levels. Scores on SA and meaningfulness increased in the maximal exposure group and decreased in the minimal and no exposure group, but changes were not statistically significant. Conclusion: The results of this study emphasize the potential of the built environment in changing SB and highlights the relevance of longer-term follow-up measurements to explore the full potential of urban redesign projects.

Identifying XAI User Needs

One aspect of a responsible application of Artificial Intelligence (AI) is ensuring that the operation and outputs of an AI system are understandable for non-technical users, who need to consider its recommendations in their decision making. The importance of explainable AI (XAI) is widely acknowledged; however, its practical implementation is not straightforward. In particular, it is still unclear what the requirements are of non-technical users from explanations, i.e. what makes an explanation meaningful. In this paper, we synthesize insights on meaningful explanations from a literature study and two use cases in the financial sector. We identified 30 components of meaningfulness in XAI literature. In addition, we report three themes associated with explanation needs that were central to the users in our use cases, but are not prominently described in literature: actionability, coherent narratives and context. Our results highlight the importance of narrowing the gap between theoretical and applied responsible AI.

Identifying XAI User Needs: Gaps between Literature and Use Cases in the Financial Sector

One aspect of a responsible application of Artificial Intelligence (AI) is ensuring that the operation and outputs of an AI system are understandable for non-technical users, who need to consider its recommendations in their decision making. The importance of explainable AI (XAI) is widely acknowledged; however, its practical implementation is not straightforward. In particular, it is still unclear what the requirements are of non-technical users from explanations, i.e. what makes an explanation meaningful. In this paper, we synthesize insights on meaningful explanations from a literature study and two use cases in the financial sector. We identified 30 components of meaningfulness in XAI literature. In addition, we report three themes associated with explanation needs that were central to the users in our use cases, but are not prominently described in literature: actionability, coherent narratives and context. Our results highlight the importance of narrowing the gap between theoretical and applied responsible AI.