Economic policy uncertainty and bankruptcy filings
研究将经济政策不确定性指标加入破产预测模型，发现能显著提高对法国、意大利、俄罗斯和西班牙企业的预测准确性，且基于推特的指数优于传统新闻指数。
Applying machine learning techniques to predict bankruptcy in the sample of French, Italian, Russian and Spanish firms, the study demonstrates that the inclusion of economic policy uncertainty (EPU) indicator into bankruptcy prediction models notably increases their accuracy. This effect is more pronounced when we use novel Twitter-based version of EPU index instead of original news-based index. We further compare the prediction accuracy of machine learning techniques and conclude that stacking ensemble method outperforms (though marginally) machine learning methods, which are more commonly used for bankruptcy prediction, such as single classifiers and bagging.