Mobile, Social, and Fashion: Three Stories from Data-Driven Design
Host
Arvind Satyanarayan
CSAIL
Abstract:
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.
Bio:
Ranjitha Kumar is an Assistant Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign (UIUC), where she leads the Data-Driven Design group. She is the recipient of a 2018 NSF CAREER award, and UIUC’s 2018 C.W. Gear Outstanding Junior Faculty Award. Her research has won best paper awards/nominations at premier conferences in HCI, and is supported by grants from Google, Amazon, and Adobe. She received her PhD from the Computer Science Department at Stanford University in 2014, and was formerly the Chief Scientist at Apropose, Inc., a data-driven design company she founded that was backed by Andreessen Horowitz and New Enterprise Associates.
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.
Bio:
Ranjitha Kumar is an Assistant Professor in the Department of Computer Science at the University of Illinois at Urbana-Champaign (UIUC), where she leads the Data-Driven Design group. She is the recipient of a 2018 NSF CAREER award, and UIUC’s 2018 C.W. Gear Outstanding Junior Faculty Award. Her research has won best paper awards/nominations at premier conferences in HCI, and is supported by grants from Google, Amazon, and Adobe. She received her PhD from the Computer Science Department at Stanford University in 2014, and was formerly the Chief Scientist at Apropose, Inc., a data-driven design company she founded that was backed by Andreessen Horowitz and New Enterprise Associates.