Bankruptcy prediction using disclosure text features

TL;DR

This paper introduces a new distress dictionary derived from managerial language in disclosures, demonstrating its effectiveness in predicting bankruptcy more accurately than existing text analysis tools.

Contribution

It develops a novel distress dictionary based on managerial sentences, improving bankruptcy prediction models beyond tone and sentiment analysis.

Findings

The distress dictionary captures unique linguistic signals.

Models using this dictionary outperform existing methods.

Disclosures contain significant predictive information.

Abstract

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.