Deep Learning for Assessing Banks’ Distress from News and Numerical Financial Data

14 Pages Posted: 28 Nov 2018

See all articles by Paola Cerchiello

Paola Cerchiello

University of Pavia - Department of Economics and Management Science

Giancarlo Nicola

University of Pavia - Department of Economics and Management Science

Samuel Rönnqvist

Åbo Akademi University - Turku Centre for Computer Science (TUCS)

Peter Sarlin

Hanken School of Economics; RiskLab Finland

Date Written: November 28, 2018

Abstract

In this paper we focus our attention on the exploitation of the information contained in financial news to enhance the performance of a classifier of bank distress. Such information should be analyzed and inserted into the predictive model in the most efficient way and this task deals with the issues related to text analysis and specifically to the analysis of news media.

Among the different models proposed for such purpose, we investigate one of the possible deep learning approaches, based on a doc2vec representation of the textual data, a kind of neural network able to map the sequence of words contained within a text onto a reduced latent semantic space. Afterwards, a second supervised neural network is trained combining news data with standard financial figures to classify banks whether in distressed or tranquil states. Indeed, the final aim is not only the improvement of the predictive performance of the classifier but also to assess the importance of news data in the classification process. Does news data really bring more useful information not contained in standard financial variables? Our results seem to confirm such hypothesis.

Keywords: Financial News, Bank Distress, Early Warning, Deep Learning, Doc2vec.

JEL Classification: C12, C83, E58, E61, G14, G21.

Suggested Citation

Cerchiello, Paola and Nicola, Giancarlo and Rönnqvist, Samuel and Sarlin, Peter, Deep Learning for Assessing Banks’ Distress from News and Numerical Financial Data (November 28, 2018). Michael J. Brennan Irish Finance Working Paper Series Research Paper No. 18-15. Available at SSRN: https://ssrn.com/abstract=3292485 or http://dx.doi.org/10.2139/ssrn.3292485

Paola Cerchiello

University of Pavia - Department of Economics and Management Science ( email )

Strada Nuova, 65
Pavia, 27100
Italy

Giancarlo Nicola (Contact Author)

University of Pavia - Department of Economics and Management Science ( email )

Strada Nuova, 65
Pavia, 27100
Italy

Samuel Rönnqvist

Åbo Akademi University - Turku Centre for Computer Science (TUCS) ( email )

Joukahaisenkatu 3-5
Turku, 20520
Finland

Peter Sarlin

Hanken School of Economics ( email )

PB 287
Helsinki, Vaasa 65101
Finland

RiskLab Finland

Turku, 20520
Finland

Register to save articles to
your library

Register

Paper statistics

Downloads
84
rank
289,819
Abstract Views
333
PlumX Metrics