Prediction of Bankruptcy with SVM Classifiers Among Retail Business Companies in EU

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43110%2F16%3A43909135" target="_blank" >RIV/62156489:43110/16:43909135 - isvavai.cz</a>

Result on the web

<a href="http://acta.mendelu.cz/media/pdf/actaun_2016064020627.pdf" target="_blank" >http://acta.mendelu.cz/media/pdf/actaun_2016064020627.pdf</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.11118/actaun201664020627" target="_blank" >10.11118/actaun201664020627</a>

Result language

angličtina

Original language name

Prediction of Bankruptcy with SVM Classifiers Among Retail Business Companies in EU

Original language description

Article focuses on the prediction of bankruptcy of the 850 medium-sized retail business companies in EU from which 48 companies gone bankrupt in 2014 with respect to lag of the used features. From various types of classifi cation models we chose Support vector machines method with linear, polynomial and radial kernels to acquire best results. Pre-processing is enhanced with fi lter based feature selection like Gain ratio, Chi-square and Relief algorithm to acquire attributes with the best information value. On this basis we deal with random samples of fi nancial data to measure prediction accuracy with the confusion matrices and area under curve values for diff erent kernel types and selected features. From the results it is obvious that with the rising distance to the bankruptcy there drops precision of bankruptcy prediction. The last year (2013) with avaible fi nancial data off ers best total prediction accuracy, thus we also infer both the Error I and II types for better recognizance. The 3rd order polynomial kernel off ers better accuracy for bankruptcy prediction than linear and radial versions. But in terms of the total accuracy we recommend to use radial kernel without feature selection.

Czech name

—

Czech description

—

Type

J_x - Unclassified - Peer-reviewed scientific article (Jimp, Jsc and Jost)

CEP classification

BB - Applied statistics, operational research

OECD FORD branch

—

Project

—

Continuities

S - Specificky vyzkum na vysokych skolach

Publication year

2016

Confidentiality

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

Name of the periodical

Acta Universitatis Agriculturae et Silviculturae Mendelianae Brunensis

ISSN

1211-8516

e-ISSN

—

Volume of the periodical

64

Issue of the periodical within the volume

2

Country of publishing house

CZ - CZECH REPUBLIC

Number of pages

8

Pages from-to

627-634

UT code for WoS article

—

EID of the result in the Scopus database

2-s2.0-84969988780