Eminent computer scientist Ed Felten has posted a short, extremely useful taxonomy of four ways that an algorithm can fail to be accountable to the people whose lives it affects: it can be protected by claims of confidentiality ("how it works is a trade secret"); by complexity ("you wouldn't understand how it works"); unreasonableness ("we consider factors supported by data, even when you there's no obvious correlation"); and injustice ("it seems impossible to explain how the algorithm is consistent with law or ethics").
The first type of explainability problem is a claim of confidentiality. Somebody knows relevant information about how a decision was made, but they choose to withhold it because they claim it is a trade secret, or that disclosing it would undermine security somehow, or that they simply prefer not to reveal it. This is not a problem with the algorithm, it's an institutional/legal problem.
The second type of explainability problem is complexity. Here everything about the algorithm is known, but somebody feels that the algorithm is so complex that they cannot understand it. It will always be possible to answer what-if questions, such as how the algorithm's result would have been different had the person been one year older, or had an extra $1000 of annual income, or had one fewer prior misdemeanor conviction, or whatever. So complexity can only be a barrier to big-picture understanding, not to understanding which factors might have changed a particular person's outcome.
The third type of explainability problem is unreasonableness. Here the workings of the algorithm are clear, and are justified by statistical evidence, but the result doesn't seem to make sense. For example, imagine that an algorithm for making credit decisions considers the color of a person's socks, and this is supported by unimpeachable scientific studies showing that sock color correlates with defaulting on credit, even when controlling for other factors. So the decision to factor in sock color may be justified on a rational basis, but many would find it unreasonable, even if it is not discriminatory in any way. Perhaps this is not a complaint about the algorithm but a complaint about the world–the algorithm is using a fact about the world, but nobody understands why the world is that way. What is difficult to explain in this case is not the algorithm, but the world that it is predicting.
The fourth type of explainability problem is injustice. Here the workings of the algorithm are understood but we think they are unfair, unjust, or morally wrong. In this case, when we say we have not received an explanation, what we really mean is that we have not received an adequate justification for the algorithm's design. The problem is not that nobody has explained how the algorithm works or how it arrived at the result it did. Instead, the problem is that it seems impossible to explain how the algorithm is consistent with law or ethics.
What does it mean to ask for an "explainable" algorithm?
[Ed Felten/Freedom to Tinker]
(Image: Simone Giertz)