Detect & Describe: Deep learning of bank stress in the news

07/25/2015
by   Samuel Rönnqvist, et al.
0

News is a pertinent source of information on financial risks and stress factors, which nevertheless is challenging to harness due to the sparse and unstructured nature of natural text. We propose an approach based on distributional semantics and deep learning with neural networks to model and link text to a scarce set of bank distress events. Through unsupervised training, we learn semantic vector representations of news articles as predictors of distress events. The predictive model that we learn can signal coinciding stress with an aggregated index at bank or European level, while crucially allowing for automatic extraction of text descriptions of the events, based on passages with high stress levels. The method offers insight that models based on other types of data cannot provide, while offering a general means for interpreting this type of semantic-predictive model. We model bank distress with data on 243 events and 6.6M news articles for 101 large European banks.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/17/2016

Bank distress in the news: Describing events through deep learning

While many models are purposed for detecting the occurrence of significa...
research
04/10/2023

Classification of news spreading barriers

News media is one of the most effective mechanisms for spreading informa...
research
06/29/2017

Deep learning bank distress from news and numerical financial data

In this paper we focus our attention on the exploitation of the informat...
research
07/03/2021

Exploring the Scope of Using News Articles to Understand Development Patterns of Districts in India

Understanding what factors bring about socio-economic development may of...
research
04/11/2019

Searching News Articles Using an Event Knowledge Graph Leveraged by Wikidata

News agencies produce thousands of multimedia stories describing events ...
research
04/02/2016

Overlay Text Extraction From TV News Broadcast

The text data present in overlaid bands convey brief descriptions of new...
research
01/03/2021

Bankruptcy prediction using disclosure text features

A public firm's bankruptcy prediction is an important financial research...

Please sign up or login with your details

Forgot password? Click here to reset