Uncovering of interesting structures in bank loan data through Bayesian networks

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F60076658%3A12510%2F15%3A43890322" target="_blank" >RIV/60076658:12510/15:43890322 - isvavai.cz</a>

Výsledek na webu

—

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

Uncovering of interesting structures in bank loan data through Bayesian networks

Popis výsledku v původním jazyce

Given the explosive growth of data collected from current business environment, data mining methods can potentially discover new business knowledge to improve managerial decision. In This paper we use relatively novel data mining approach that employs discrete Bayesian network methodology to discover knowledge from data. More concretely we try to uncover structure and relationship among some socio-economic characteristics gathered by bank institution and credit risk in some sample of credit applicants.All data were collected during the 2013 - 2014. For this purpose we used two algorithms for Bayesian network structure discovering, namely hill climbing and growth-shrinking algorithms with a priori assigned relationship among some subset of socio-economics variables. The resulting structure was compared to others to BN. As a best BN model was identified structure without any implied restriction and derived by hill-climbing algorithm. BIC score for our best model was -13147.55. This "bes

Název v anglickém jazyce

Uncovering of interesting structures in bank loan data through Bayesian networks

Popis výsledku anglicky

Given the explosive growth of data collected from current business environment, data mining methods can potentially discover new business knowledge to improve managerial decision. In This paper we use relatively novel data mining approach that employs discrete Bayesian network methodology to discover knowledge from data. More concretely we try to uncover structure and relationship among some socio-economic characteristics gathered by bank institution and credit risk in some sample of credit applicants.All data were collected during the 2013 - 2014. For this purpose we used two algorithms for Bayesian network structure discovering, namely hill climbing and growth-shrinking algorithms with a priori assigned relationship among some subset of socio-economics variables. The resulting structure was compared to others to BN. As a best BN model was identified structure without any implied restriction and derived by hill-climbing algorithm. BIC score for our best model was -13147.55. This "bes

Druh

D - Stať ve sborníku

CEP obor

BB - Aplikovaná statistika, operační výzkum

OECD FORD obor

—

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2015

Kód důvěrnosti údajů

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

Název statě ve sborníku

ICABR 2015, X. International Conference on Applied Business Research

ISBN

978-80-7509-379-0

ISSN

—

e-ISSN

—

Počet stran výsledku

887

Strana od-do

881

Název nakladatele

Mendelova univerzita v Brně

Místo vydání

Brno

Místo konání akce

Madrid

Datum konání akce

14. 9. 2015

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—