What question did this study set out to answer?

This research focuses on how understanding predictions from machine learning models can build trust.

August 8, 2016

"Why Should I Trust You?"

Key Points

This research focuses on how understanding predictions from machine learning models can build trust.
Discusses the characteristics of machine learning models as black boxes.
Analyzes the significance of model transparency in aiding decision-making.
Examines strategies for transforming untrustworthy predictions into reliable outputs.
Establishes that understanding predictions enhances user trust in machine learning applications.
Highlights that insights gained from model transparency can improve prediction accuracy.
Suggests that trust is crucial for the deployment of machine learning models.

Abstract

Despite widespread adoption, machine learning models remain mostly black boxes. Understanding the reasons behind predictions is, however, quite important in assessing trust, which is fundamental if one plans to take action based on a prediction, or when choosing whether to deploy a new model. Such understanding also provides insights into the model, which can be used to transform an untrustworthy model or prediction into a trustworthy one.

Ask AI

Mark Helpful

Bookmark

Relay