Modeliranje korelacija u kreditnom portfelju

master's thesis

• Author: Katarina Bačić
• Mentor: Siniša Slijepčević (mentor)
• Committee member: Siniša Slijepčević (predsjednik povjerenstva)
• Committee member: Goran Muić (član povjerenstva)
• Committee member: Maja Starčević (član povjerenstva)
• Committee member: Boris Širola (član povjerenstva)
• Granter: University of Zagreb; Faculty of Science; (Department of Mathematics); Zagreb
• Defense date and country: 2016-09-23, Croatia
• Scientific / art field, discipline and subdiscipline: NATURAL SCIENCES; Mathematics

Abstract

U ovom diplomskom radu cilj je pružiti pristupačan uvod u temelje modeliranja kreditnog portfelja. Krećemo do osnovnih pojmova iz vjerojatnosti i statistike, a zatim postupno ulazimo u svijet upravljanja kreditnim rizikom kroz pojmove očekivanog i neočekivanog gubitka, gdje možemo vidjeti i bitnu ulogu korelacija, te distribucije gubitka i načina kako je dobiti. Zatim, krećemo s modeliranjem koreliranih defaulta pomoću dva pristupa. Uz teoretsku podlogu, upoznajemo i modele predstavnike tih pristupa. Također, specifikacijom uvodimo jednofaktorski (CreditMetrics\(^{TM}\) /KMV), odnosno jednosektorski (CreditRisk\(^+\)) model te nakon njihove usporedbe završavamo praktičnim primjerom.

Abstract (english)

This thesis goal is to provide accessible introduction to the foundations of the credit portfolio modelling. We start from the basic concepts of probability and statistics, and then gradually enter the world of credit risk management through the terms of the expected and unexpected loss (where we first see the important role of the correlations), distribution loss and ways to get it. Then, we use two approaches to the modeling of correlated defaults and get introduced to representatives of these approaches. We also look in more detail at portfolios with uniform dependency structure, namely one-factor (CreditMetrics \(^{TM}\) /KMV), respectively one-sector (CreditRisk\(^+\)) models and after their comparison we conclude this thesis with working example

• Keywords: modeliranje kreditnog portfelja; upravljanje kreditnim rizikom; modeliranje koreliranih defaulta; jednofaktorski model; jednosektorski model
• Keywords (english): credit portfolio modelling; credit risk management; modeling of correlated defaults; one-factor model; one-sector model
• Language: croatian
• URN:NBN: urn:nbn:hr:217:683082
• Study programme: Title: Finance and Business Mathematics; Study programme type: university; Study level: graduate; Academic / professional title: magistar/magistra matematike (magistar/magistra matematike)
• Type of resource: Text
• File origin: Born digital
• Access conditions: Open access
• Created on: 2017-05-09 10:43:33