AI Explainability 360: Impact and Design

As artificial intelligence and machine learning algorithms become increasingly prevalent in society, multiple stakeholders are calling for these to provide explanations. At the same time, stakeholders, whether they be affected citizens, government regulators, domain experts, or system developers, have different explanation needs. To address needs, 2019, we created AI Explainability 360, an open source software toolkit featuring ten diverse state-of-the-art explainability methods two evaluation metrics. This paper examines impact of with several case studies, statistics, community feedback. The ways which users experienced 360 resulted types improvements metrics, highlighted by adoption independent LF & Data Foundation. also describes flexible design toolkit, examples its use, significant educational material documentation available users.