BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:iCalendar-Ruby
BEGIN:VEVENT
CATEGORIES:Talks and Lectures
DESCRIPTION:The Jackson School's Academic Workshop Series will host a prese
 ntation from Huifeng Su\, a PhD student at the Yale School of Management\, 
 "Reuniting Forcibly Separated Families Through Shared Memories with Machine
  Learning." The Student Academic Workshop Series at the Jackson School of G
 lobal Affairs is a bi-weekly forum in which advanced undergraduate and grad
 uate students can present their research projects and receive constructive 
 feedback from their peers.\n\nOver 100\,000 victims rely on self-reported\,
  semi-structured clues on humanitarian service platforms to search for thei
 r missing parent or child. Yet\, these searches face vast candidate spaces 
 and poor-quality reporting. While related to the information retrieval and 
 entity matching literature\, existing methods\, including LLM-based approac
 hes\, are not designed to search effectively when the underlying data are i
 ncomplete and inaccurate. Huifeng Su and collaborators developed a domain a
 dapted machine learning pipeline that leverages textual and numerical infor
 mation\, enabling nuanced matching on incomplete and inconsistent data. The
 ir locally deployable\, cost-free solution significantly outperforms LLM–ba
 sed methods in both search quality and runtime\, effectively narrowing sear
 ch spaces and enhancing human matching effectiveness. In doing so\, it adva
 nces the design and operation of family reunification service.\n\nHuifeng S
 u is a Ph.D. candidate in operations at the Yale School of Management\, co-
 advised by professors Lesley Meng and Edieal J. Pinker. Leveraging structur
 ed and unstructured data\, Su’s research focuses on improving and evaluatin
 g the efficiency\, quality\, and equity of essential health and human servi
 ces (HHS). Su adapts causal inference and machine learning methods to speci
 fic operational contexts to generate actionable insights. Prior to his doct
 oral studies\, Su studied industrial and systems engineering and computer s
 ciences at the University of Wisconsin-Madison.
DTEND:20260224T203000Z
DTSTAMP:20260312T160812Z
DTSTART:20260224T193000Z
GEO:41.315434;-72.922388
LOCATION:Horchow Hall\, Seminar Room (106)
SEQUENCE:0
SUMMARY:Reuniting Forcibly Separated Families Through Shared Memories with 
 Machine Learning
UID:tag:localist.com\,2008:EventInstance_51260937166346
URL:https://events.jackson.yale.edu/event/reuniting-forcibly-separated-fami
 lies-through-shared-memories-with-machine-learning
END:VEVENT
END:VCALENDAR