Can Linguistic Text Mining Technology Further Improve the Prediction Capability of Corporate Credit Default (original) (raw)

2015

Abstract

We apply text mining (TM) techniques to extract and quantify relevant Chinese financial news, in an attempt to further develop the classical early warning models of financial distress. We extend the work of Demers and Vega (2011) by proposing a measure of the degree of credit default, referred to as the ‘distress intensity of default-corpus ’ (DIDC), and investigate the predictive power of DIDC on default probability by incorporating it into the signaling model, along with the classical financial performance variables (liquidity, debt, activity and profitability ratios). We construct a logistic regression (LR) model to better integrate the DIDC and financial performance variables into a more effective early warning signal model, with the incorporation of DIDC into the LR model revealing a significant reduction in Type I errors and an apparent increase in classification accuracy, thereby proving the effectiveness of the additional information from TM on financial corpus, and also con...

Ralph Lu hasn't uploaded this paper.

Let Ralph know you want this paper to be uploaded.

Ask for this paper to be uploaded.