Predicting distresses using deep learning of text segments in annual reports

TY - JOUR

T1 - Predicting distresses using deep learning of text segments in annual reports

AU - Matin, Rastin

AU - Hansen, Casper

AU - Hansen, Christian

AU - Mølgaard, Pia

PY - 2019

Y1 - 2019

N2 - Corporate distress models are central to regulators and financial institutions that need to evaluate the default risk of corporate firms. They are traditionally only based on the numerical financial variables in the firms’ annual reports. In this paper we develop a model that employs the unstructured textual data in the reports as well, namely the auditors’ reports and managements’ statements. Our model consists of a convolutional recurrent neural network which, when concatenated with the numerical financial variables, learns a descriptive representation of the text that is suited for corporate distress prediction. We find that the unstructured data provides a statistically significant enhancement of the distress prediction performance, in particular for large firms where accurate predictions are of the utmost importance. Furthermore, we find that auditors’ reports are more informative than managements’ statements and that a joint model including both managements’ statements and auditors’ reports displays no enhancement relative to a model including only auditors’ reports. Our model demonstrates a direct improvement over existing state-of-the-art models in the field of distress modelling.

AB - Corporate distress models are central to regulators and financial institutions that need to evaluate the default risk of corporate firms. They are traditionally only based on the numerical financial variables in the firms’ annual reports. In this paper we develop a model that employs the unstructured textual data in the reports as well, namely the auditors’ reports and managements’ statements. Our model consists of a convolutional recurrent neural network which, when concatenated with the numerical financial variables, learns a descriptive representation of the text that is suited for corporate distress prediction. We find that the unstructured data provides a statistically significant enhancement of the distress prediction performance, in particular for large firms where accurate predictions are of the utmost importance. Furthermore, we find that auditors’ reports are more informative than managements’ statements and that a joint model including both managements’ statements and auditors’ reports displays no enhancement relative to a model including only auditors’ reports. Our model demonstrates a direct improvement over existing state-of-the-art models in the field of distress modelling.

KW - Convolutional neural networks

KW - Corporate default prediction

KW - Natural language processing

KW - Recurrent neural networks

UR - http://www.scopus.com/inward/record.url?scp=85065489352&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2019.04.071

DO - 10.1016/j.eswa.2019.04.071

M3 - Journal article

AN - SCOPUS:85065489352

SN - 0957-4174

VL - 132

SP - 199

EP - 208

JO - Expert Systems with Applications

JF - Expert Systems with Applications

ER -