On logit and artificial neural networks in corporate distress modelling for Zimbabwe listed corporates
Corporate financial distress prediction is a pivotal aspect of economic development. The ability to foretell that a company will be getting into financial distress is essential for decision-makers, shareholders, and policymakers in making the best decisions and policies for sustainable development....
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-01-01
|
| Series: | Sustainability Analytics and Modeling |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2667259622000042 |
| Summary: | Corporate financial distress prediction is a pivotal aspect of economic development. The ability to foretell that a company will be getting into financial distress is essential for decision-makers, shareholders, and policymakers in making the best decisions and policies for sustainable development. Prediction accuracy is of paramount importance in the implementation of distress mitigation measures, a critical component attracting investment in particular to most of the developing countries in Africa. The advent of the fourth industrial revolution saw Artificial Intelligence (AI) taking centre stage in financial risk modelling. This growth has however not precluded the role of traditional statistical methods in modelling financial risk. There is a lack of consensus amongst academia and practitioners on the accuracy of these two groups of methodologies in distress prediction. Protagonists of the conventional school of thought still hold on to statistical methods being more accurate whilst the new age proponents believe AI has brought in higher levels of predictive strength and model accuracy. This study seeks to compare the accuracy of Logit and Artificial Neural Networks (ANN) in corporate distress prediction. The two modelling techniques were applied to an 8-year panel dataset from the Zimbabwe Stock Exchange. The Logit model outperformed the ANN by an overall accuracy of 92.21% compared to ANN with 85.8%. Heightened prediction accuracy is bound to improve the return to shareholders by enhancing financial risk management within emerging markets. This study also seeks to contribute to the ongoing debate on the superiority between AI techniques and statistical techniques. |
|---|---|
| ISSN: | 2667-2596 |