An End-to-end Approach to Human-Centered Data Science
Abstract:
Human-Centered Data Science is a new frontier that emerges right into the intersection of computer and information sciences, statistics, behavioral economics, and other human sciences. It is concerned with building scalable data-driven solutions to problems that are of the people, by the people, and for the people. We consider an end-to-end approach extremely powerful in such a practice, which collects data from the daily tasks of human subjects, understands their objectives and behaviors through statistical and data mining tools, makes accurate predictions with human-in-the-loop machine learning, draws explainable and actionable insights, and builds large-scale interventions to optimize the outcomes of these data owners at their original tasks. Such an approach creates tremendous opportunities to integrate and innovate methodologies within the computational fields and across disciplines.
In this talk, I will introduce our recent effort in building and deploying end-to-end data science solutions in various real-world contexts (e.g., pro-social lending, gig economy, and open source software development) to improve productivity-related outcomes and promote social good in these scenarios. I will also briefly cover our attempt to create an innovative curriculum for applied data science.
Bio:
Qiaozhu Mei a professor in the School of Information and the Department of EECS at the University of Michigan, where he served as the founding director of the Master of Applied Data Science program, one of the first online degree programs at the University of Michigan. His research group develops novel methods in machine learning, data mining, information retrieval, and natural language processing and applies them to diverse real-world domains, such as the Web, social media, healthcare, and education, with the aim to improve people's daily lives. His work has received multiple best paper awards at ICML, WWW, WSDM, KDD, and other major conferences in computing. Qiaozhu is an ACM Distinguished Member. He has served as the General Co-Chair of SIGIR 2018 and currently serves on the editorial board of the Journal of Machine Learning Research and the ACM Transactions on the Web.