Open the Black Box Data-Driven Explanation of Black Box Decision Systems

By Dino Pedreschi, Fosca Giannotti, Riccardo Guidotti, Anna Monreale, Luca Pappalardo, Salvatore Ruggieri, Franco Turini. 2018

39 citations recorded by the source corpus.

Black box systems for automated decision making, often based on machine learning over (big) data, map a user's features into a class or a score without exposing the reasons why. This is problematic not only for lack of transparency, but also for possible biases hidden in the algorithms, due to human prejudices and collection artifacts hidden in the training data, which may lead to unfair or wrong decisions. We introduce the local-to-global framework for black box explanation, a novel approach with promising early results, which paves the road for a wide spectrum of future developments along three dimensions: (i) the language for expressing explanations in terms of highly expressive logic-based rules, with a statistical and causal interpretation; (ii) the inference of local explanations aimed at revealing the logic of the decision adopted for a specific instance by querying and auditing the black box in the vicinity of the target instance; (iii), the bottom-up generalization of the many local explanations into simple global ones, with algorithms that optimize the quality and comprehensibility of explanations.

Subfields: Artificial Intelligence, Information Systems and Management

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Information Systems and Management

Citations in the corpus

Meaningful Explanations of Black Box AI Decision Systems (2019, background): “Many controversial cases have already highlighted that dele-gating decision-making to black box algorithms is critical in many sensitive domains, including crime prediction, personality scoring, image classiﬁcation, personal assistance, and more (Pedreschi et al. 2018).”