Credit Rating Change Modeling Using News and Financial Ratios

Abstract

Credit ratings convey credit risk information to participants in financial markets, including investors, issuers, intermediaries, and regulators. Accurate credit rating information plays a crucial role in supporting sound financial decision-making processes. Most previous studies on credit rating modeling are based on accounting and market information. Text data are largely ignored despite the potential benefit of conveying timely information regarding a firm’s outlook. To leverage the additional information in news full-text for credit rating prediction, we designed and implemented a news full-text analysis system that provides firm-level coverage, topic, and sentiment variables. The novel topic-specific sentiment variables contain a large fraction of missing values because of uneven news coverage. The missing value problem creates a new challenge for credit rating prediction approaches. We address this issue by developing a missing-tolerant multinomial probit (MT-MNP) model, which imputes missing values based on the Bayesian theoretical framework. Our experiments using seven and a half years of real-world credit ratings and news full-text data show that (1) the overall news coverage can explain future credit rating changes while the aggregated news sentiment cannot; (2) topic-specific news coverage and sentiment have statistically significant impact on future credit rating changes; (3) topic-specific negative sentiment has a more salient impact on future credit rating changes compared to topic-specific positive sentiment; (4) MT-MNP performs better in predicting future credit rating changes compared to support vector machines (SVM). The performance gap as measured by macroaveraging F-measure is small but consistent.