The design and validation of an intuitive confidence measure

van der Waa, J.S.; van Diggelen, J.; Neerincx, M.A.

doi:10.1145/1235

The design and validation of an intuitive confidence measure

Title

The design and validation of an intuitive confidence measure

Author

van der Waa, J.S.
van Diggelen, J.
Neerincx, M.A.

Contributor

Said, A. (editor)
Komatsu, T. (editor)

Publication year

2018

Abstract

Explainable AI becomes increasingly important as the use of intelligent systems becomes more widespread in high-risk domains. In these domains it is important that the user knows to which degree the system’s decisions can be trusted. To facilitate this, we present the Intuitive Confidence Measure (ICM): A lazy learning meta-model that can predict how likely a given decision is correct. ICM is intended to be easy to understand which we validated in an experiment. We compared ICM with two different methods of computing confidence measures: The numerical output of the model and an actively learned metamodel. The validation was performed using a smart assistant for maritime professionals. Results show that ICM is easier to understand but that each user is unique in its desires for explanations. This user studies with domain experts shows what users need in their explanations and that personalization is crucial. © 2018

Subject

Certainty
Confidence
Experiment
Explainability
ICM
Instance based
Lazy learning
Machine learning
Measure
User
Validation
Experiments
Learning systems
Numerical methods
User interfaces
Certainty
Confidence
Explainability
Instance based
Lazy learning
Measure
User
Validation
Intelligent systems