Index Errans

person in Black box

Brent Mittelstadt

Counterfactual explanation

in Black box

Brent Mittelstadt, data ethicist at the Oxford Internet Institute (and, at the time, University College London's Science and Technology Studies department). A co-author of Counterfactual Explanations Without Opening the Black Box and of the companion GDPR right-to-explanation paper; his work centres on AI ethics, data protection, and the ethics of algorithms.

Stake§

Academic and reform-oriented, with public research funding; no commercial conflict.

Mittelstadt is a co-author of the counterfactual- explanation paper, which for this topic reframes a right to understand an automated decision as a right to know what to change. His broader survey work on the ethics of algorithms maps the normative side of algorithmic opacity that Pasquale argues from the law-and-power direction.

Works in this corpus§

their concepts on the territory
Counterfactual explanationCounterfactual explanation

1 concept in this scholar's webopen the full territory →

excerpts

explanations can, in principle, be offered without opening the 'black box.' Looking at explanations as a means to help a data subject act rather than merely understand, one could gauge the scope and content of explanations according to the specific goal or action they are intended to support.
— Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR (2018)

The legal move that matches the technical one: drop the demand to see inside the model, and ask instead what the person needs in order to act. An [[concept:explainability|explanation]] is judged by the recourse it enables, not by the mechanism it reveals.

on Counterfactual explanation, Explainability

You were denied a loan because your annual income was £30,000. If your income had been £45,000, you would have been offered a loan.
— Counterfactual Explanations Without Opening the Black Box: Automated Decisions and the GDPR (2018)

A [[concept:counterfactual-explanation|counterfactual explanation]] in one line: the smallest change to the inputs that would have flipped the decision. It tells the subject what to change without disclosing — or even requiring — the model's internals.

on Counterfactual explanation