We’re excited to announce that Amazon SageMaker Clarify supports online explainability by providing explanations for machine learning (ML) model’s individual predictions in near real-time on live endpoints. SageMaker Clarify gives ML developers greater visibility into their training data and models so they can identify potential bias and explain predictions. ML models may consider some feature inputs more strongly than others when generating predictions. SageMaker Clarify provides scores detailing which features contributed the most to your model’s individual prediction after the model has been run on new data. These details can help determine if a particular input features has more influence on the model predictions than expected. You can view these details for each prediction in real-time via online explainability or get a report in bulk that utilize batch processing of all the individual predictions. This new feature reduces latency for explanations from minutes to seconds or less. The possibilities for real-time explanations are broad. For example, customer service representatives can better understand the reasons why a customer may churn when they call for help resolving a problem in real time. As the representative learns more about the nature of the customer’s issue and enters that data, real-time explanations can provide updated reasoning for suggested resolutions.