BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Colloquium
DESCRIPTION:Joint colloquium with Operations\, Technology & Information Man
 agement\, Cornell SC Johnson College of Business\n\nRecommendations in the 
 NYC High School Match (and other high-stakes settings)\n\nRecommendation an
 d search systems are now used in high-stakes settings\, including to help f
 ind jobs\, schools\, and partners. Building public interest recommender sys
 tems in such settings bring both individual-level (enabling exploration\, d
 iversity\, data quality) and societal (fairness\, capacity constraints\, mo
 noculture) challenges. I will talk about an ongoing collaboration with the 
 NYC Public Schools\, in which we designed and deployed an informational int
 ervention to help students from underserved middle schools discover high-pe
 rforming\, nearby high schools where they have a strong individual admissio
 ns likelihood. However\, recommending specific programs brings a methodolog
 ical challenge\, congestion: if many applicants are recommended the same pr
 ogram\, affecting admissions likelihoods\, then the recommendations may be 
 self-defeating. Time permitting\, I'll also overview other directions in ta
 ckling such challenges\, including (a) algorithmic monoculture and LLM homo
 geneity\, (b) a platform to help discharge patients to long-term care facil
 ities\, (c) feed ranking algorithms on Bluesky for research paper recommend
 ations.\n \n\nBio: Nikhil Garg is an assistant professor of operations rese
 arch and information engineering at Cornell Tech as part of the Jacobs Inst
 itute. He uses algorithms\, data science\, and economics approaches to stud
 y democracy\, markets\, and societal systems at large. Nikhil has received 
 the NSF CAREER\, INFORMS George Dantzig Dissertation Award\, an honorable m
 ention for the ACM SIGecom dissertation award\, and paper awards including 
 Computer-Supported Cooperative Work (CSCW)\, Equity and Access in Algorithm
 s\, Mechanisms\, and Optimization (EAAMO)\, and Conference on Health\, Infe
 rence\, and Learning (CHIL). He received his Ph.D. from Stanford University
  and has spent considerable time collaborating with government agencies and
  non-profits. His work has been supported by the NSF\, NASA\, Sloan Foundat
 ion\, and other organizations.
DTEND:20260310T211500Z
DTSTAMP:20260511T100710Z
DTSTART:20260310T201500Z
GEO:42.443451;-76.481506
LOCATION:Frank H. T. Rhodes Hall\, 253
SEQUENCE:0
SUMMARY:ORIE Colloquium: Nikhil Garg (Cornell ORIE / Cornell Tech)
UID:tag:localist.com\,2008:EventInstance_51818051340882
URL:https://events.cornell.edu/event/orie-colloquium-nikhil-garg-cornell-or
 ie-cornell-tech
END:VEVENT
END:VCALENDAR