Last week we got to host our third monthly virtual meetup
. More than 70 attendees from all around the world got to hear about “Explainable Workflows using Python”:
This talk approaches the typical data science workflow with a focus on explainability. Simply put, it focuses on skills and tactics used to help data scientists articulate their findings to end-users, stake-holders, and other data scientists. From data ingestion, cleaning and feature selection, and ultimately model selection, explainability can be incorporated into a data scientists workflow. Using a combination of semi-automated and open source software, this talk walks you through an explainable workflow.
Our presenter was Austin Eovito
, a Data Scientist on the Technical Marketing and Evangelism team in San Francisco, California. As a recent graduate student of Florida State University, Austin is focused on the balance of bleeding-edge research produced by academia and the tools used in applied data science. His Masters thesis was on White Collar Crime using Time-aware Joint-Topic-Sentiment Analysis (TTS), and his areas of interests are NLP, applied data science, and Explainable AI. Austin currently resides in San Francisco, with his fiancé, dog, and two cats.
Please review the slides
(PDF) and watch the video recording below. We encountered some connectivity issues in the beginning, so please excuse the choppy audio during the first couple of minutes. Luckily, the introductory chat with Austin, his talk, and the Q&Q session afterwards were not affected.
Unlike traditional webinars, our monthly virtual meetups are structured to combine great data science and AI content with the opportunity for community members to meet each other, hang out with speakers and panelists, and make new connections in an informal setting using small-group video chat breakout sessions. Don’t miss our August event, which will be announced over the coming days.
Questions? Feedback? Join the discussion
over on the forum.#virtualmeetup#explainability#Python#Hands-on#Hands-on-feature