| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font
First page > Show document

Show document Help

Title:Ocenjevanje verjetnosti neplačila za kredite prebivalstvu : nelinearen pristop s samoorganizirajočimi se mrežami
Authors:ID Jagrič, Vita (Author)
ID Kračun, Davorin (Mentor) More about this mentor... New window
Files:.pdf DR_Jagric_Vita_2012.pdf (1,95 MB)
MD5: A5677E65DAAE3DBF5C056EF9FC70807B
PID: 20.500.12556/dkum/a00ebf13-eca6-4fdb-bcac-ed8f5d7dd28d
 
Language:Slovenian
Work type:Dissertation
Typology:2.08 - Doctoral Dissertation
Organization:EPF - Faculty of Business and Economics
Abstract:V disertaciji obravnavamo najstarejšo obliko finančnega tveganja, to je kreditno tveganje. Ko se kreditnemu tveganju izpostavljajo sodobne banke v močno medsebojno povezanem finančnem sistemu, se ustvarja prostor za nastanek sistemskega tveganja. Kapital banke je v tovrstnih razmerah še odgovorneje postavljen v vlogo varovala pred prenašanjem nepričakovanih izgub med bankami. Baselski sporazumi v vsaki svoji različici krepijo odvisnost zahtevanega kapitala od prevzetega tveganja. S tem nastane potreba po zelo natančni kvantifikaciji tveganj, ki jih je prevzela banka. Kvalitetna in ustrezna ocena parametrov tveganja v nekem portfelju je tako temeljni pogoj delujoče in učinkovite kapitalske regulacije. Izboljšanje klasifikacijske sposobnosti modela kreditnega tveganja, temeljnega graditelja v procesu ocene kapitalskih zahtev, bi tako lahko prispevala k izboljšanju učinkovitosti ugotavljanja kapitalskih zahtev. Disertacija predstavlja doprinos k védenju o kreditnem tveganju na področju portfelja potrošniških kreditov prebivalstvu. Za namen obvladovanja kreditnega tveganja s pomočjo klasifikacije kreditnih vlog je bilo v literaturi predstavljenih veliko kvantitativnih metod, med najpopularnejšimi so statistične metode. Razloge za priljubljenost logistične regresije, ki je v praksi najbolj uporabljana metoda za vprašanje modeliranja kreditnega tveganja na portfeljih kreditov prebivalstvu, gre iskati predvsem v poznavanju metode, preprostosti uporabe ter zadovoljivih rezultatih glede na potrebno ekspertno znanje. Kljub temu ne gre za najboljšo rešitev. Logistična regresija ima številne pomanjkljivosti, kar se pokaže tudi v tej disertaciji, kjer jo uporabimo za izdelavo primerjalnih modelov. Literatura nakazuje, da lahko boljšo klasifikacijsko sposobnost dosežejo tehnike nelinearnih metod, denimo metode podpornih vektorjev, nevronskih mrež, mehke logike itd. Osnovna teza te disertacije je, da klasifikacijski model za portfelj kreditov prebivalstvu, ki izključno ali deloma uporablja metodo samoorganizirajočih se mrež, deluje bolje kot klasični model, ki je logistična regresija. Najprej smo ocenili model z uporabo metode LVQ, ki je metoda iz družine samoorganizirajočih se mrež. Nato smo ocenili primerjalne modele. V disertaciji se posvetimo tudi vprašanju definiranja kvalitete modela, ki je ključno za možnost primerjave med dvema različnima rešitvama. Pokazano je, da je klasifikacijska točnost lahko najboljša mera kvalitete modela, saj ne posega pristransko v rezultat modela. Če pri interpretaciji rezultata modela ni potrebno vnašati nobene subjektivnosti, potem velja tudi, da dobi uporabnik enoznačen in transparenten odgovor o razvrstitvi kreditnih vlog. Ob primerjavi obeh alternativ se osnovna teza disertacije izkaže kot utemeljena, saj je model LVQ dosegel višjo klasifikacijsko točnost kot primerjalni model. Uspešnost metode pripisujemo prisotnosti nelinearnosti v podatkih. Pomen prispevka disertacije se kaže v možnosti takojšnjega prenosa ugotovitev v prakso. Uporaba metode, ki izboljšuje klasifikacijsko sposobnost modela kreditnega tveganja, predstavlja za banke možnost znižanja prihodnjih stroškov zaradi slabih kreditov ter znižanja oportunitetih stroškov zaradi zavrnitve potencialno dobrih kreditov. Uporaba izboljšanih modelov kreditnega tveganja prispeva k večji stabilnosti bančnega sistema in izboljšanem razmerju med dejanskim tveganjem v portfelju in zahtevanim kapitalom. Disertacija je predstavljena v slovenskem jeziku, s čimer utrjuje in razvija slovensko terminološko zakladnico.
Keywords:kreditno tveganje prebivalstva, verjetnost neplačila, samoorganizirajoče se mreže, vektorska kvantizacija
Place of publishing:Maribor
Publisher:V. Jagrič
Year of publishing:2011
PID:20.500.12556/DKUM-20304 New window
UDC:336.77
COBISS.SI-ID:20848102 New window
NUK URN:URN:SI:UM:DK:BCRFIJN6
Publication date in DKUM:04.06.2012
Views:4184
Downloads:709
Metadata:XML RDF-CHPDL DC-XML DC-RDF
Categories:EPF
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share


Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Secondary language

Language:English
Title:Estimating probability of default for retail credit: nonlinear approach with self-organizing maps
Abstract:The presented dissertation considers the oldest form of financial risk, namely the credit risk. When modern banks are exposed to credit risk in the context of the highly interconnected financial system, it creates room for the emergence of systemic risk. That being said, the capital of the bank is set in the function of the buffer against unexpected losses and finally preventing transfer of losses among banks. With the implementation of Basel II capital accord, the amount of capital is directly linked to the risk of a bank’s single portfolio. From this definition the need for very precise quantification of risks arises. Good quality of risk evaluation and the exact estimation of portfolio’s risk parameters is a prerequisite for effective capital regulation at the microprudential as well as macroprudential level. An improvement of the credit classification model quality would therefore contribute to an improvement of the process of capital requirement’s assessment. In this thesis we propose an alternative methodology when modeling credit risk for a retail consumer credit portfolio of a commercial bank in order to raise the quality of the risk assessment. The dissertation contributes to the knowledge regarding credit risk in a portfolio of consumer loans to households. For the purpose of credit application classification there were many quantitative methods presented in the literature, among which the most popular include statistical methods. In business practice most widely used method for modeling credit risk in retail portfolios is the logistic regression. The reasons for its popularity may lie on one hand in the fact that it is wide-known among bankers and on the other hand in its simple application and satisfactory results when considering the undemanding level of expert knowledge needed for the implementation. Due to its popularity, we applied the logistic regression for modeling benchmarking models. However, it is neither the best nor the only and final solution. Logistic regression has many shortcomings, which are also commented on in this dissertation. A review of the literature suggests that a better classification accuracy can be achieved by applying non-linear methods such as support vector machines, neural networks, fuzzy logic etc. The thesis of this dissertation proposes that a classification model for a retail portfolio of consumer loans, which exclusively or partly uses self-organizing networks, may outperform a standard solution, namely a logistic regression model. First, we trained a network using the learning vector quantization, a method from the family of self-organizing networks. Next, we estimated the benchmarking models. In this dissertation we focus also on the issue of the definition of a model’s quality, which was crucial for the ability of the comparison between two very different solutions. We argue that the classification accuracy is the best measure of the model’s quality, as there is no subjectivity and prejudice to the outcome. Provided that the interpretation of the model results does not include any human interference, the user gets a unique and transparent response to the classification problem of credit applications. When comparing both alternatives the thesis of this dissertation turns out to be proper, since the LVQ model achieved higher classification accuracy compared to benchmarking model. We assign the success of the LVQ method to the presence of non-linearity in the data. The importance of this dissertation’s contribution manifests itself also in the ability of immediate transfer of findings into business practice. Using the method that improves the classification accuracy of a credit risk model introduces for banks the possibility of reducing the future costs of non-performing loans and reduction in opportunity costs of a rejected potentially good credit. Furthermore, improved credit risk models contribute to greater stability of the banking system and an improved relationship between the actual risk in the portfolio and the required capital.
Keywords:retail credit risk, probability of default, self-organizing maps, learning vector quantization


Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica