**Coffee is served at the in-person seminar**
A recording of the talk will be posted afterwards on our YouTube channel at https://www.youtube.com/channel/UCN0kf0sI01-FXPZdWAA-uMA
Title: Candidates Rediscovery through Job Requisitions Matching - A Data Science POC at Workday
This talk aims to walk the audience through a Data Science prototyping pipeline developed at Workday for the Candidates Rediscovery use case. Talent sourcing is a time-consuming and often futile process for many recruiters. The pipeline addresses this pain point by surfaces selected, active candidates who applied for past similar job openings. Algorithms include TF-IDF, Doc2Vec, and Shingling. The audience will also get a glimpse into Workday's Machine Learning standard operating procedure from ideation to productization.
Katharina Huang is a Data Scientist for the Machine Learning Organization within Workday. After receiving her MS in Biostatistics in 2010, she served as a survey operations specialist at the University of Michigan, using statistical methods to optimize operational timelines and sampling designs of national K-12 surveys. Katie pivoted into the tech industry in 2016 and attended the Metis Data Science Bootcamp. Since then, she has worked on NLP techniques for human capital management and anomaly detection, retail sales prediction with parallel computing, and computer vision deep learning.
101 Howard St, University of San Francisco - Downtown Campus, San Francisco, CA 94105