Explainable Artificial Intelligence for Predictive Maintenance Applications using a Local Surrogate Model
Andrea Torcianti, Stephan Matzka
Abstract
This paper provides an explanatory interface using Local Interpretable Model-agnostic Explanations (LIME) for a predictive maintenance dataset. The explanations are evaluated and the explanatory quality of the model is compared to two previous explainable models for the same dataset.
Topics & Concepts
Computer scienceExplanatory modelArtificial intelligenceMachine learningPredictive modellingQuality (philosophy)Data modelingData miningStatisticsMathematicsSoftware engineeringEpistemologyPhilosophyExplainable Artificial Intelligence (XAI)Machine Learning and Data ClassificationTopic Modeling