BEGIN:VCALENDAR
VERSION:2.0
PRODID:icalendar-ruby
CALSCALE:GREGORIAN
X-WR-CALNAME:Reuniting Forcibly Separated Families Through Shared Memories 
 with Machine Learning
X-WR-TIMEZONE:Eastern Time (US & Canada)
BEGIN:VEVENT
DTSTAMP:20260516T022342Z
UID:tag:localist.com\,2008:EventInstance_51260937166346
DTSTART:20260224T193000Z
DTEND:20260224T203000Z
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 Machi
 ne Learning." The Student Academic Workshop Series at the Jackson School o
 f Global Affairs is a bi-weekly forum in which advanced undergraduate and 
 graduate students can present their research projects and receive construc
 tive feedback from their peers.\n\nOver 100\,000 victims rely on self-repo
 rted\, semi-structured clues on humanitarian service platforms to search f
 or their missing parent or child. Yet\, these searches face vast candidate
  spaces and poor-quality reporting. While related to the information retri
 eval and entity matching literature\, existing methods\, including LLM-bas
 ed approaches\, are not designed to search effectively when the underlying
  data are incomplete and inaccurate. Huifeng Su and collaborators develope
 d a domain adapted machine learning pipeline that leverages textual and nu
 merical information\, enabling nuanced matching on incomplete and inconsis
 tent data. Their locally deployable\, cost-free solution significantly out
 performs LLM–based methods in both search quality and runtime\, effectiv
 ely narrowing search spaces and enhancing human matching effectiveness. In
  doing so\, it advances the design and operation of family reunification s
 ervice.\n\nHuifeng Su is a Ph.D. candidate in operations at the Yale Schoo
 l of Management\, co-advised by professors Lesley Meng and Edieal J. Pinke
 r. Leveraging structured and unstructured data\, Su’s research focuses o
 n improving and evaluating the efficiency\, quality\, and equity of essent
 ial health and human services (HHS). Su adapts causal inference and machin
 e learning methods to specific operational contexts to generate actionable
  insights. Prior to his doctoral studies\, Su studied industrial and syste
 ms engineering and computer sciences at the University of Wisconsin-Madiso
 n.
GEO:41.315434;-72.922388
LOCATION:Horchow Hall\, Seminar Room (106)
SUMMARY:Reuniting Forcibly Separated Families Through Shared Memories with 
 Machine Learning
URL;VALUE=URI:https://events.jackson.yale.edu/event/reuniting-forcibly-sepa
 rated-families-through-shared-memories-with-machine-learning
CATEGORIES:Talks and Lectures
END:VEVENT
END:VCALENDAR