Next Article in Journal
What Future for the Green Bond Market? How Can Policymakers, Companies, and Investors Unlock the Potential of the Green Bond Market?
Next Article in Special Issue
The Application of Graphic Methods and the DEA in Predicting the Risk of Bankruptcy
Previous Article in Journal
CEO Diversity, Political Influences, and CEO Turnover in Unstable Environments: The Romanian Case
Previous Article in Special Issue
Assessment of Bankruptcy Risk of Large Companies: European Countries Evolution Analysis
 
 
Article
Peer-Review Record

Support Vector Machine Methods and Artificial Neural Networks Used for the Development of Bankruptcy Prediction Models and their Comparison

J. Risk Financial Manag. 2020, 13(3), 60; https://doi.org/10.3390/jrfm13030060
by Jakub Horak *, Jaromir Vrbka and Petr Suler
Reviewer 1: Anonymous
J. Risk Financial Manag. 2020, 13(3), 60; https://doi.org/10.3390/jrfm13030060
Submission received: 29 January 2020 / Revised: 19 March 2020 / Accepted: 23 March 2020 / Published: 24 March 2020
(This article belongs to the Special Issue Modern Methods of Bankruptcy Prediction)

Round 1

Reviewer 1 Report

This paper uses Support Vector Machine and artificial neural networks methods to predict bankruptcy in Czech Republic. The results show that artificial neural networks are much more accurate than SVM in predicting possible bankruptcy.

 

I find the paper well developed and written. The two approaches are applied and contrasted. I suggest including additional macroeconomic indicators in the predictive model to account for business cycles or institutional changes. Moreover, how do the models perform in the out-of-sample forecasting?  

 

For the comparison of the two kinds of models, you may want to provide more explanations for the strengths and weakness, and show why NM would outperform SVM.

Author Response

Dear reviewer,

Please find attached all necessary information.

Thank you for your feedback.

With kind regards

Jakub Horak

Author Response File: Author Response.pdf

Reviewer 2 Report

See file attached

Comments for author File: Comments.pdf

Author Response

Dear reviewer,

Please find attached all necessary information.

Thank you for your feedback.

With kind regards

Jakub Horak

Author Response File: Author Response.pdf

Back to TopTop