Quality indexes of predictive models in risk and portfolio management

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216224%3A14310%2F09%3A00036102" target="_blank" >RIV/00216224:14310/09:00036102 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Quality indexes of predictive models in risk and portfolio management

Popis výsledku v původním jazyce

For a measurement of partial processes of a financial institution, especially their components like scoring models or other predictive models, it is possible to use quantitative indexes such as Gini index, K-S statistics, Lift and Information statistics.They can be used for comparison of several developed models at the moment of development. It is possible to use them for monitoring of quality of models after the deployment into real business as well. The outcome is then an effective tool to attract new creditworthy customers, and at the same time, control losses. This paper deals with definition of good/bad client, which is crucial for further computations. The main part is devoted to quality indexes based on distribution functions and on density functions. It brings some interesting results connected to Lift in general and for normally distributed data. An application on real data is included too.

Název v anglickém jazyce

Quality indexes of predictive models in risk and portfolio management

Popis výsledku anglicky

For a measurement of partial processes of a financial institution, especially their components like scoring models or other predictive models, it is possible to use quantitative indexes such as Gini index, K-S statistics, Lift and Information statistics.They can be used for comparison of several developed models at the moment of development. It is possible to use them for monitoring of quality of models after the deployment into real business as well. The outcome is then an effective tool to attract new creditworthy customers, and at the same time, control losses. This paper deals with definition of good/bad client, which is crucial for further computations. The main part is devoted to quality indexes based on distribution functions and on density functions. It brings some interesting results connected to Lift in general and for normally distributed data. An application on real data is included too.

Druh

D - Stať ve sborníku

CEP obor

BB - Aplikovaná statistika, operační výzkum

OECD FORD obor

—

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2009

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

IMAEF 2009 Proceedings

ISBN

978-960-233-196-5

ISSN

1791-9800

e-ISSN

—

Počet stran výsledku

12

Strana od-do

—

Název nakladatele

Department of Economics, University of Ioannina

Místo vydání

Ioannina, Greece

Místo konání akce

Ioannina, Greece

Datum konání akce

11. 6. 2009

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—