Having access to the right types of data at scale is increasingly the key to designing innovation. In this talk, I'll discuss how my group has created original datasets for three domains — mobile app design, fashion retail, and social networks — and leveraged them to build novel user experiences.
First, I'll present a system for capturing and aggregating interaction data from third-party Android apps to identify effective mobile design patterns: open sourcing analytics that were previously locked away. Next, I'll discuss fashion data collected with Wizard of Oz chatbots, used to model deep learning frameworks for automating personal styling advice. Finally, I'll introduce an emoji-based social media designed to incentivize curation and map the "taste graph" of its users.
Ranjitha Kumar is the Chief Research Scientist at UserTesting, and an Assistant Professor in the Computer Science Department at the University of Illinois at Urbana-Champaign (UIUC). She is the recipient of a 2018 NSF CAREER award; a 2019 Dean’s Award for Excellence in Research from UIUC's Grainger College of Engineering; and the 2018 C.W. Gear Outstanding Junior Faculty Award from UIUC's Computer Science Department. Her research has won best paper awards/nominations at premier conferences in HCI, and is supported by grants from the NSF, Google, Amazon, and Adobe. She received her BS and PhD from the Computer Science Department at Stanford University, and co-founded Apropose, Inc., a data-driven design startup based on her dissertation work that was backed by Andreessen Horowitz and New Enterprise Associates.