BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//132.216.98.100//NONSGML kigkonsult.se iCalcreator 2.20.4//
BEGIN:VEVENT
UID:20251121T174342EST-0620miuf9x@132.216.98.100
DTSTAMP:20251121T224342Z
DESCRIPTION:Title: Multilayer Network Analysis for Improved Credit Risk Pre
 diction.\n\nAbstract: We present a multilayer network model for credit ris
 k assessment. Our model accounts for multiple connections between borrower
 s (such as their geographic location and their economic activity) and allo
 ws for explicitly modelling the interaction between connected borrowers. W
 e develop a multilayer personalized PageRank algorithm that allows quantif
 ying the strength of the default exposure of any borrower in the network. 
 We test our methodology in an agricultural lending framework\, where it ha
 s been suspected for a long time default correlates between borrowers when
  they are subject to the same structural risks. Our results show there are
  significant predictive gains just by including centrality multilayer netw
 ork information to the model\, and these gains are increased by more compl
 ex information such as the multilayer PageRank variables. The results sugg
 est default risk is highest when an individual is connected to many defaul
 ters\, but this risk is mitigated by the size of the neighborhood of the i
 ndividual\, showing both default risk and financial stability propagate th
 roughout the network.\n\n \n\n \n\nSeminar Quantact\n	Zoom\n
DTSTART:20220429T140000Z
DTEND:20220429T150000Z
SUMMARY:María Óskarsdóttir\, Reykjavik University
URL:/mathstat/channels/event/maria-oskarsdottir-reykja
 vik-university-339276
END:VEVENT
END:VCALENDAR