ABSTRACT
Recently, various corporate failure prediction models that use machine learning techniques have received considerable attention. In particular, using a sequence of a company's historical information, rather than just the most recent information, yields better predictive performance by adopting recurrent neural networks (RNNs) and long short-term memory (LSTM) algorithms in the United States market. Similarly, we evaluate whether these results hold in emerging market contexts using listed companies in Korea. We also compare the logistic regression, random forest, RNN, LSTM, and an ensemble model combining these four techniques. The random forest model with recent information outperforms the other models, indicating that corporate failure prediction models for immature markets, unlike those for developed markets, might have to focus more on recent information rather than on the historical sequence of corporate performance.
Acknowledgements
We appreciate the helpful comments and support from Linda Allen, Jonathan Batten, Robert Webb, and all participants of the 2022 SKKU International Conference: Trends in Digital Economy and Finance. This work (Kim) was supported by the 2021 Yeungnam University Research Grant. This research (Ryu) was supported by the MSIT(Ministry of Science and ICT), Korea, under the ICAN(ICT Challenge and Advanced Network of HRD) programme (IITP-2022-2020-0-01816) supervised by the IITP (Institute of Information & Communications Technology Planning & Evaluation).
Disclosure statement
No potential conflict of interest was reported by the authors.
Notes
1 FOMC Press Conference (January 26, 2022).
2 This reclassification was made in accordance with the UNCTAD Trade and Development Board decision TD/B/68/3.
3 In Korea, some companies listed on the KOSDAQ market can switch to the KOSPI market. These switches occur because the KOSDAQ market is known as a market for small and medium-sized businesses, which are riskier than the companies listed on the KOSPI.