PREDICTING BANKRUPTCY USING ARTIFICIAL INTELLIGENCE: THE CASE OF THE ENGINEERING INDUSTRY

Bankruptcy prediction is a powerful earlywarning tool and plays a crucial role in various aspects of financial and business management. It is vital for safeguarding investments, maintaining financial stability, making informed credit decisions, and contributing to the overall health of the economy....

Full description

Saved in:
Bibliographic Details
Published in:Economics & sociology 2023-10, Vol.16 (4), p.178-190
Main Authors: Letkovsky, Stanislav, Jencova, Sylvia, Vasanicova, Petra, Gavura, Stefan, Bacik, Radovan
Format: Article
Language:English
Subjects:
Accuracy
Artificial intelligence
Bankruptcy
Decision making
Discriminant analysis
Engineering
Forecasting
Investments
Machinery
Neural networks
Organizational effectiveness
Prediction models
Probability distribution
Regression analysis
Social networks
Statistical methods
Support vector machines
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Bankruptcy prediction is a powerful earlywarning tool and plays a crucial role in various aspects of financial and business management. It is vital for safeguarding investments, maintaining financial stability, making informed credit decisions, and contributing to the overall health of the economy. This paper aims to develop bankruptcy prediction models for die Slovak engineering industry and to compare thir effectiveness. Predictions are generated using the classical logistic regression (LR) method as well as artificial intelligence (AI) techniques (artificial neural networks (ANN) and support vector machines (SVM)). Research sample consists of 825 businesses operating in the engineering industry (Manufacture of machinery and equipment n.e.c.; Manufacture of motor vehicles, trailers and semi-trailers; Manufacture of other transport equipment). The selection of eight financial indicators is grounded in prior research and existing literature. The results show high accuracy for all used methods. The SVM outcomes indicate a level of accuracy on the test set that is nearly indistinguishable from that of die ANN model. The use of AI techniques demonstrates their effective predictive capabilities and holds a significant position within the realm of tools for forecasting bankruptcy.
ISSN:2071-789X
2306-3459
DOI:10.14254/2071789X.2023/16-4/8