Bankruptcy prediction using disclosure text features
This work provides an incremental improvement in bankruptcy prediction for financial analysts and investors by introducing a novel text-based feature set.
This paper addresses the problem of predicting public firm bankruptcy using disclosure text features. It proposes a new distress dictionary derived from managers' explanations of financial status, demonstrating significant linguistic differences between bankrupt and non-bankrupt firms. Predictive models built using features from this dictionary achieved the highest accuracy compared to two existing financial text analysis dictionaries.
A public firm's bankruptcy prediction is an important financial research problem because of the security price downside risks. Traditional methods rely on accounting metrics that suffer from shortcomings like window dressing and retrospective focus. While disclosure text-based metrics overcome some of these issues, current methods excessively focus on disclosure tone and sentiment. There is a requirement to relate meaningful signals in the disclosure text to financial outcomes and quantify the disclosure text data. This work proposes a new distress dictionary based on the sentences used by managers in explaining financial status. It demonstrates the significant differences in linguistic features between bankrupt and non-bankrupt firms. Further, using a large sample of 500 bankrupt firms, it builds predictive models and compares the performance against two dictionaries used in financial text analysis. This research shows that the proposed stress dictionary captures unique information from disclosures and the predictive models based on its features have the highest accuracy.