Publication
Communicating Uncertainty in Machine Learning Explanations: A Visualization Analytics Approach for Predictive Process Monitoring
Nijat Mehdiyev; Maxim Majlatow; Peter Fettke
In: L. Longo (Hrsg.). Second World Conference on Explainable Artificial Intelligence. xAI: World Conference on Explainable Artificial Intelligence (xAI), July 17-19, Valletta, Malta, Pages 420-438, Communications in Compute, Springer, Cham, 2024.
Abstract
As data-driven intelligent systems advance, the need for reliable and transparent decision-making mechanisms has become increasingly important. Therefore, it is essential to integrate uncertainty quantification and model explainability approaches to foster trustworthy business and operational process analytics. This study explores how model uncertainty can be effectively communicated in global and local post-hoc explanation approaches. Furthermore, this study examines appropriate visualization analytics approaches to facilitate such methodological integration. By combining these two research directions, decision-makers can not only justify the plausibility of explanation-driven actionable insights but also validate their reliability. Finally, the study includes expert interviews to assess the suitability of the proposed approach and designed interface for a real-world predictive process monitoring problem in the manufacturing domain.
Projekte
Green-AI Hub Mittelstand - Green-AI Hub Mittelstand,
EINHORN - Entwicklung von menschenzentrierten Systemen zur dialogorientierten Interaktion mit erklärbaren KI-Methoden für Prozessintelligenz
EINHORN - Entwicklung von menschenzentrierten Systemen zur dialogorientierten Interaktion mit erklärbaren KI-Methoden für Prozessintelligenz