On the appropriate thresholds in the logistic regression bankruptcy model

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F62156489%3A43110%2F24%3A43925249" target="_blank" >RIV/62156489:43110/24:43925249 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1063/5.0210401" target="_blank" >https://doi.org/10.1063/5.0210401</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1063/5.0210401" target="_blank" >10.1063/5.0210401</a>

Jazyk výsledku

angličtina

Název v původním jazyce

On the appropriate thresholds in the logistic regression bankruptcy model

Popis výsledku v původním jazyce

This article focuses on the identification of a potential threshold for logistic regression models for bankruptcy prediction in the forestry sector in cases where the ratio of active and bankrupt companies in the dataset is not balanced. Model estimates are performed on a random selection of 300 active forest companies in EU countries along with eight (and 17) bankruptcy companies in 2019 (and in 2018). Analyzes are performed on the basis of accounting (micro) data of companies from the Orbis database. Empirical results show that in cases where bankruptcies are in the minority, it is necessary to replace the commonly used threshold with an optimized threshold, which will emphasize the balancing of the error rate in both the group of active and the group of bankrupt companies.

Název v anglickém jazyce

On the appropriate thresholds in the logistic regression bankruptcy model

Popis výsledku anglicky

This article focuses on the identification of a potential threshold for logistic regression models for bankruptcy prediction in the forestry sector in cases where the ratio of active and bankrupt companies in the dataset is not balanced. Model estimates are performed on a random selection of 300 active forest companies in EU countries along with eight (and 17) bankruptcy companies in 2019 (and in 2018). Analyzes are performed on the basis of accounting (micro) data of companies from the Orbis database. Empirical results show that in cases where bankruptcies are in the minority, it is necessary to replace the commonly used threshold with an optimized threshold, which will emphasize the balancing of the error rate in both the group of active and the group of bankrupt companies.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10103 - Statistics and probability

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2024

Kód důvěrnosti údajů

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

Název statě ve sborníku

AIP Conference Proceedings 3094

ISBN

978-0-7354-4954-1

ISSN

0094-243X

e-ISSN

—

Počet stran výsledku

4

Strana od-do

100003

Název nakladatele

American Institute of Physics (AIP)

Místo vydání

Melville

Místo konání akce

Herákleion

Datum konání akce

19. 9. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001244923000090