BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Memento EPFL//
BEGIN:VEVENT
SUMMARY:Transfer Learning for Mobile Phone Credit Scoring
DTSTART:20180626T163000
DTSTAMP:20260509T052334Z
UID:ae9a785434d57993c6e7590b46b262380df00248993e71b07480e343
CATEGORIES:Conferences - Seminars
DESCRIPTION:Skyler Speakman\nMobile money platforms are gaining traction 
 across developing markets as a convenient way of sending and receiving mon
 ey over mobile phones. Recent joint collaborations between banks and mobil
 e-network operators leverage a customer’s past mobile phone transactions
  in order to create a credit score for the individual. In this work\, we a
 ddress the problem of launching a mobile-phone based credit scoring system
  in a new market without the marginal distribution of features of borrower
 s in the new market. This challenge rules out traditional transfer learnin
 g approaches such as a direct covariate shift.  This work was recently pr
 esented at ACM COMPASS 2018.\n\nSkyler Speakman is a Research Scientist 
 at IBM Research -- Africa.  He is the technical lead for A.I. at the Ken
 ya lab.  His projects use data science  and machine learning to impact t
 he lives of millions of people on the continent. Skyler completed a Ph.D
 . in Information Systems at Carnegie Mellon University as well as a M.S. i
 n Machine Learning.  He also holds masters in Mathematics\, Statistics\, 
 and Public Policy.  He lives in Nairobi\, Kenya with his wife and two you
 ng sons. \n 
LOCATION:CE 1 2 https://plan.epfl.ch/?room==CE%201%202
STATUS:CONFIRMED
END:VEVENT
END:VCALENDAR