원문정보
피인용수 : 0건 (자료제공 : 네이버학술정보)
초록
영어
This study examines the predictability of various machine learning and deep learning models in corporate default forecasts. Using a sample of U.S. corporate defaults over the period of 1963-2020, we find Ensemble classifier and Bi-LSTM classifier forecast the corporate bankruptcy better than other models and the predictability of the Ensemble classifier is more stable in year-to-year variability. Further, machine learning models outperform deep learning models in high yield grade samples, while deep learning models performs better than machine learning models in investment grade samples.
목차
Abstract
1. Introduction
2. Data
3. Empirical Method
3.3. Machine Learning for Classification
3.4. Deep Learning for Classification
3.5 Optimal Hyperparameters and Cross Validation
4. Empirical Results
4.1. Predictability Test with Whole Data Set
4.2. Predictability Test with Year-split Data Set
4.3. Predictability Test with Rating-split Data Set
5. Conclusion
References
1. Introduction
2. Data
3. Empirical Method
3.3. Machine Learning for Classification
3.4. Deep Learning for Classification
3.5 Optimal Hyperparameters and Cross Validation
4. Empirical Results
4.1. Predictability Test with Whole Data Set
4.2. Predictability Test with Year-split Data Set
4.3. Predictability Test with Rating-split Data Set
5. Conclusion
References
저자정보
참고문헌
자료제공 : 네이버학술정보