Financial Distress Prediction: Zmijewski (1984) vs. Data Mining

D 2020

Financial Distress Prediction: Zmijewski (1984) vs. Data Mining

ŠTĚRBA, Martin and Ladislav ŠIŠKA

Basic information

Original name

Financial Distress Prediction: Zmijewski (1984) vs. Data Mining

Authors

ŠTĚRBA, Martin (203 Czech Republic, belonging to the institution) and Ladislav ŠIŠKA (203 Czech Republic, belonging to the institution)

Edition

Brno, Proceedings of the International Scientific Conference of Business Economics Management and Marketing 2019, p. 200-208, 9 pp. 2020

Publisher

Ekonomicko-správní fakulta MU

Other information

Language

English

Type of outcome

Stať ve sborníku

Field of Study

50204 Business and management

Country of publisher

Czech Republic

Confidentiality degree

není předmětem státního či obchodního tajemství

Publication form

electronic version available online

References:

URL

RIV identification code

RIV/00216224:14560/20:00115274

Organization unit

Faculty of Economics and Administration

ISBN

978-80-210-9565-6

Keywords (in Czech)

finanční tíseň; úpadek; konkurz; dat mining; neuronové sítě

Keywords in English

financial distress; data mining; neural networks; bankruptcy

Abstract

V originále

The study re-estimates the Zmijewski's (1984) prediction model of financial distress with techniques offered by data miners. Namely logistic regression, neural network and decision tree models are applied to the training dataset consisting of approx. 130 thousand annual observations of financial ratios from non-financial companies residing in Czechia. Area under ROC curve (AUC) computed from similarly large independent testing set served as a measure of the predictive power of each alternative model. Our findings reveal the potential of neural networks to slightly, but statistically significantly increase the prediction power of the model. But this benefit goes in expense of complexity and lower interpretability of neural networks.

Links

MUNI/A/1156/2018, interní kód MU

Name: Komparace výkonnosti podniků s využitím nejen finančních dat (Acronym: KVPVND)

Investor: Masaryk University, Category A

Citovat

ŠTĚRBA, Martin and Ladislav ŠIŠKA. Financial Distress Prediction: Zmijewski (1984) vs. Data Mining. Online. In Ing. Petr Mikuš, Ph.D. Proceedings of the International Scientific Conference of Business Economics Management and Marketing 2019. Brno: Ekonomicko-správní fakulta MU, 2020, p. 200-208. ISBN 978-80-210-9565-6.

@inproceedings{1614657,
   author = {Štěrba, Martin and Šiška, Ladislav},
   address = {Brno},
   booktitle = {Proceedings of the International Scientific Conference of Business Economics Management and Marketing 2019},
   editor = {Ing. Petr Mikuš, Ph.D.},
   keywords = {financial distress; data mining; neural networks; bankruptcy},
   howpublished = {elektronická verze "online"},
   language = {eng},
   location = {Brno},
   isbn = {978-80-210-9565-6},
   pages = {200-208},
   publisher = {Ekonomicko-správní fakulta MU},
   title = {Financial Distress Prediction: Zmijewski (1984) vs. Data Mining},
   url = {https://webcentrum.muni.cz/media/3220002/sbornik-2019-105-converted.pdf},
   year = {2020}
}

TY  - JOUR
ID  - 1614657
AU  - Štěrba, Martin - Šiška, Ladislav
PY  - 2020
TI  - Financial Distress Prediction: Zmijewski (1984) vs. Data Mining
PB  - Ekonomicko-správní fakulta MU
CY  - Brno
SN  - 9788021095656
KW  - financial distress
KW  - data mining
KW  - neural networks
KW  - bankruptcy
UR  - https://webcentrum.muni.cz/media/3220002/sbornik-2019-105-converted.pdf
L2  - https://webcentrum.muni.cz/media/3220002/sbornik-2019-105-converted.pdf
N2  - The study re-estimates the Zmijewski's (1984) prediction model of financial distress with techniques offered by data miners. Namely logistic regression, neural network and decision tree models are applied to the training dataset consisting of approx. 130 thousand annual observations of financial ratios from non-financial companies residing in Czechia. Area under ROC curve (AUC) computed from similarly large independent testing set served as a measure of the predictive power of each alternative model. Our findings reveal the potential of neural networks to slightly, but statistically significantly increase the prediction power of the model. But this benefit goes in expense of complexity and lower interpretability of neural networks.
ER  -

ŠTĚRBA, Martin and Ladislav ŠIŠKA. Financial Distress Prediction: Zmijewski (1984) vs. Data Mining. Online. In Ing. Petr Mikuš, Ph.D. \textit{Proceedings of the International Scientific Conference of Business Economics Management and Marketing 2019}. Brno: Ekonomicko-správní fakulta MU, 2020, p.~200-208. ISBN~978-80-210-9565-6.

Detailed Information on Publication Record