Predicting regional credit ratings using ensemble classification with metacost

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216275%3A25410%2F19%3A39914921" target="_blank" >RIV/00216275:25410/19:39914921 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-030-19810-7_33" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-030-19810-7_33</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-030-19810-7_33" target="_blank" >10.1007/978-3-030-19810-7_33</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Predicting regional credit ratings using ensemble classification with metacost

Popis výsledku v původním jazyce

Ensemble classifiers are learning algorithms that combine sets of base classifiers in order to increase their diversity and, thus, decrease variance and achieve better predictive performance compared to single classifiers. Previous research has shown that ensemble classifiers are more accurate than single classifiers in predicting credit ratings. Here we deal with highly imbalanced multi-class data of regional entities. To overcome these problems, we propose a novel hybrid model combining data oversampling and cost-sensitive ensemble classification. This paper demonstrates that the use of the SMOTE technique to balance the multi-class data solves the imbalance problem effectively. Different misclassification cost assigned in cost matrix solves the problem of ordered classes. This approach is combined with ensemble classification within the MetaCost framework. We show that more accurate prediction can be achieved using this approach in terms of average cost and area under ROC. This paper provides empirical evidence on the dataset of 451 regions classified into 8 rating classes, as obtained from the Moody’s rating agency. The results show that Random Forest combined with MetaCost outperforms the rest of the base classifiers, as well as other benchmark methods.

Název v anglickém jazyce

Predicting regional credit ratings using ensemble classification with metacost

Popis výsledku anglicky

Ensemble classifiers are learning algorithms that combine sets of base classifiers in order to increase their diversity and, thus, decrease variance and achieve better predictive performance compared to single classifiers. Previous research has shown that ensemble classifiers are more accurate than single classifiers in predicting credit ratings. Here we deal with highly imbalanced multi-class data of regional entities. To overcome these problems, we propose a novel hybrid model combining data oversampling and cost-sensitive ensemble classification. This paper demonstrates that the use of the SMOTE technique to balance the multi-class data solves the imbalance problem effectively. Different misclassification cost assigned in cost matrix solves the problem of ordered classes. This approach is combined with ensemble classification within the MetaCost framework. We show that more accurate prediction can be achieved using this approach in terms of average cost and area under ROC. This paper provides empirical evidence on the dataset of 451 regions classified into 8 rating classes, as obtained from the Moody’s rating agency. The results show that Random Forest combined with MetaCost outperforms the rest of the base classifiers, as well as other benchmark methods.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach<br>I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2019

Kód důvěrnosti údajů

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

Název statě ve sborníku

Artificial Intelligence Methods in Intelligent Algorithms : Proceedings of 8th Computer Science On-line Conference 2019, Vol. 2

ISBN

978-3-030-19809-1

ISSN

2194-5357

e-ISSN

—

Počet stran výsledku

11

Strana od-do

332-342

Název nakladatele

Springer Nature

Místo vydání

Heidelberg

Místo konání akce

Praha

Datum konání akce

24. 4. 2019

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000503762800033