Predicting distresses using deep learning of text segments in annual reports

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Standard

Predicting distresses using deep learning of text segments in annual reports. / Matin, Rastin; Hansen, Casper; Hansen, Christian; Mølgaard, Pia.

I: Expert Systems with Applications, Bind 132, 2019, s. 199-208.

Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt

Harvard

Matin, R, Hansen, C, Hansen, C & Mølgaard, P 2019, 'Predicting distresses using deep learning of text segments in annual reports', Expert Systems with Applications, bind 132, s. 199-208. https://doi.org/10.1016/j.eswa.2019.04.071

APA

Matin, R., Hansen, C., Hansen, C., & Mølgaard, P. (2019). Predicting distresses using deep learning of text segments in annual reports. Expert Systems with Applications, 132, 199-208. https://doi.org/10.1016/j.eswa.2019.04.071

Vancouver

Matin R, Hansen C, Hansen C, Mølgaard P. Predicting distresses using deep learning of text segments in annual reports. Expert Systems with Applications. 2019;132:199-208. https://doi.org/10.1016/j.eswa.2019.04.071

Author

Matin, Rastin ; Hansen, Casper ; Hansen, Christian ; Mølgaard, Pia. / Predicting distresses using deep learning of text segments in annual reports. I: Expert Systems with Applications. 2019 ; Bind 132. s. 199-208.

Bibtex

@article{82583c29edf8423dbc36be8dc57eaaa9,
title = "Predicting distresses using deep learning of text segments in annual reports",
abstract = "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{\textquoteright} annual reports. In this paper we develop a model that employs the unstructured textual data in the reports as well, namely the auditors{\textquoteright} reports and managements{\textquoteright} 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{\textquoteright} reports are more informative than managements{\textquoteright} statements and that a joint model including both managements{\textquoteright} statements and auditors{\textquoteright} reports displays no enhancement relative to a model including only auditors{\textquoteright} reports. Our model demonstrates a direct improvement over existing state-of-the-art models in the field of distress modelling.",
keywords = "Convolutional neural networks, Corporate default prediction, Natural language processing, Recurrent neural networks",
author = "Rastin Matin and Casper Hansen and Christian Hansen and Pia M{\o}lgaard",
year = "2019",
doi = "10.1016/j.eswa.2019.04.071",
language = "English",
volume = "132",
pages = "199--208",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Pergamon Press",

}

RIS

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

U2 - 10.1016/j.eswa.2019.04.071

DO - 10.1016/j.eswa.2019.04.071

M3 - Journal article

AN - SCOPUS:85065489352

VL - 132

SP - 199

EP - 208

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

ER -

ID: 223137101