AI is helping us to work and live more efficiently, but while AI comes with benefits, it also comes with risks. When data is biased, AI systems created from that data are also biased, which can cause unintended harm to vulnerable populations. Understanding how to prevent and/or mitigate these biases using technical and non-technical solutions will help organizations develop more trustworthy AI applications and reduce the possibility of harm. We will discuss how different types of bias can be unintentionally laced into an AI system and how the SAS® analytics platform, SAS® Viya® 4, allows users to assess the fairness and bias in a model.
