Women in Data Science Blacksburg at Virginia Tech will support and encourage women pursuing careers in data science. This event is sponsored by Nielsen and the Virginia Tech program in Computational Modeling and Data Analytics in the Academy of Integrated Science. All genders are invited and encouraged to participate in this event, which features women speakers.

There will be keynote talks by Milinda Lakkam (senior data scientist at LinkedIn) and Sally Morton (dean of the Virginia Tech College of Science), a tutorial on data visualization by Jennifer Van Mullekom (associate professor of practice in statistics at Virginia Tech), a tutorial on deep learning by Cheryl Danner (member of technical staff at Expedition Technology), a career panel, and plenty of opportunities for networking including dinner.

Open to all, but there are limited spots available, so register soon!

Schedule of events at Holtzman Alumni Center:

• Registration, 3:00 - 3:30, Lobby outside assembly hall
• Welcome, 3:30 - 3:40, Assembly hall
• Keynote Speaker: Milinda Lakkam, "Detecting automation on LinkedIn's platform," 3:40 - 4:05, Assembly hall
• Career Panel, 4:05 - 5:00, Assembly hall
• Break , 5:00 - 5:20, Grand hall
• Keynote Speaker: Sally Morton , "Bias," 5:20 - 5:45, Assembly hall
• Dinner with breakout discussion groups, 5:45 - 7:00, Museum
• Introductory track tutorial: Jennifer Van Mullekom, "Data Visualization", 7:00 - 8:15, Assembly hall
• Advanced track tutorial: Cheryl Danner, "Focal-loss-based Deep Learning for Object Detection," 7-8:15, 2nd floor board room

Abstracts:

Keynote talk "Detecting automation on LinkedIn’s platform"

The use of automation to steal LinkedIn member data and send spam invitations/messages violates our terms of service and the privacy expectations of our members. In this talk we outline the process and tools we use to tackle this problem — feature engineering, generation of seed labels, outlier detection methods, and external feedback to improve our labels.

Advanced track tutorial "Focal -loss-based Deep Learning for Object Detection"

Deep learning has revolutionized image processing, but at this point, it can be used for so much more than classifying pictures of dogs. This tutorial will introduce a few applications in computer vision and signal processing where deep learning is rapidly advancing the state of the art. We will discuss techniques for building better custom deep learning systems with an emphasis on focal loss. To run the interactive focal loss example, bring a laptop that can run TensorFlow and scikit-learn in a Jupyter notebook.