Incorporating explainability and fairness-awareness in ML solutions (Level 300)
Machine learned models and data-driven systems are being increasingly used to help make decisions in application domains such as financial services, healthcare, education, and human resources. With the goal that a significant portion of these decision systems becoming fully-automated, there is need for understanding and rectifying the underlying bias in data, algorithms, and objectives, including providing reliable explanations for the predictions and decisions taken by these machine learning (ML) systems. In this session, we share how Amazon SageMaker Clarify address some of the regulatory, business and data science questions that arise in the context of explainability and fairness in ML. We would also specifically dive deep into how builders can incorporate these best practices in explainable and fairness-aware ML into their solutions using these AWS services.
Sujoy Roy, Senior Data Scientist, AWS