Senior Editor: Gediminas Adomavicius

University of Minnesota

Term: June 1, 2018 – December 31, 2020


Research Interests

Much of my research has focused on providing computational solutions to aid decision making in data and information intensive environments. This encompasses a variety of problem settings, including: personalization technologies and recommender systems; machine learning and data mining techniques; electronic market mechanisms.

Some of my recent projects have dealt with: understanding and improving different performance aspects of recommendation algorithms; designing real time bidder support schemes in combinatorial and multi attribute auctions and analyzing their impact; developing efficient computational strategies for dynamic inventory liquidation problems; adapting machine learning techniques to address important healthcare problems; accounting for measurement error and misclassification in variables generated via data mining; and understanding unintended consequences of consumer interactions with recommender systems.


Research Methodologies

Much of my work uses design science oriented methodologies, with an emphasis on computational problem solving and experimentation, algorithm development, machine learning / predictive analytics, as well as lab experiments.


Email: gedas@umn.edu