BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Predictably Unequal? The Effects of Machine Learning on Credit Mar
 kets
DTSTART:20181211T120000
DTEND:20181211T130000
DTSTAMP:20260415T024311Z
UID:980c7c15dd2475c4902a20406ae2437062b78a2b97ac3e23354d15f7
CATEGORIES:Conferences - Seminars
DESCRIPTION:Andreas FUSTER\, Swiss National Bank\nInnovations in statistic
 al technology\, including in predicting creditworthiness\, have sparked co
 ncerns about differential impacts across categories such as race. Theoreti
 cally\, distributional consequences from better statistical technology can
  come from greater flexibility to uncover structural relationships\, or fr
 om triangulation of otherwise excluded characteristics. Using data on US m
 ortgages\, we predict default using traditional and machine learning model
 s. We find that Black and Hispanic borrowers are disproportionately less l
 ikely to gain from the introduction of machine learning. In a simple equil
 ibrium credit market model\, machine learning increases disparity in rates
  between and within groups\; these changes are primarily attributable to g
 reater flexibility.
LOCATION:UNIL\, Extranef\, room 126 https://planete.unil.ch/plan/?local=EX
 T-126
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR