Abstract: 

As AI becomes more prevalent in our everyday lives, it is our responsibility to make sure that these systems are built in an ethical fashion. One component of responsible AI is a proactive approach to interpretability and explainability at all phases of an AI project’s lifecycle.

In this presentation, we will dive into different phases of a machine learning project and highlight features that promote interpretability and explainability. Specifically, we will look at the data preparation and processing, modeling, and continuous monitoring phases of the lifecycle and show how practitioners or organizations can build features to empower their data science teams.

Bio: 

Scott Reed is an applied AI ethicist at DataRobot. He has a background in applied information technology and international relations and has worked in different capacities in and around data his whole career. Prior to DataRobot, he worked as a data scientist at Fannie Mae. He is passionate about solving complex business problems using advanced Data Science techniques and finding insights that produce effective outcomes.