Semantic XAI for contextualized demand forecasting explanations
This work addresses the need for transparent and actionable explanations in demand forecasting for domain practitioners, though it is incremental as it applies existing semantic technologies to a specific domain.
The paper tackled the problem of providing interpretable explanations for demand forecasting models by proposing a semantic XAI architecture that integrates knowledge graphs and ontologies, resulting in a system that generates contextualized explanations without exposing sensitive model details and makes the developed ontology and dataset publicly available.
The paper proposes a novel architecture for explainable AI based on semantic technologies and AI. We tailor the architecture for the domain of demand forecasting and validate it on a real-world case study. The provided explanations combine concepts describing features relevant to a particular forecast, related media events, and metadata regarding external datasets of interest. The knowledge graph provides concepts that convey feature information at a higher abstraction level. By using them, explanations do not expose sensitive details regarding the demand forecasting models. The explanations also emphasize actionable dimensions where suitable. We link domain knowledge, forecasted values, and forecast explanations in a Knowledge Graph. The ontology and dataset we developed for this use case are publicly available for further research.