2019
DOI: 10.1111/acfi.12453
|View full text |Cite
|
Sign up to set email alerts
|

Discovering bank risk factors from financial statements based on a new semi‐supervised text mining algorithm

Abstract: This paper aims to comprehensively uncover bank risk factors from qualitative textual risk disclosures reported in financial statements, which contain a huge amount of information on bank risks. We propose a new semi-supervised text mining approach named naive collision algorithm to analyse the textual risk disclosures, which can more accurately identify bank risk factors compared with the typical unsupervised text mining approach. We identified 21 bank risk factors in total, which is far more than identified … Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
19
0

Year Published

2019
2019
2022
2022

Publication Types

Select...
5
3

Relationship

1
7

Authors

Journals

citations
Cited by 58 publications
(24 citation statements)
references
References 39 publications
0
19
0
Order By: Relevance
“…As a result of mergers, rising banks combine more and hence have lower returns. Some recent developments in this area of literature (Adesina, 2019;Aysan and Disli, 2019;Bustamante et al, 2019;Dang, 2019;Jiang et al, 2020;Nguyen & Dang, 2020;Sobarsyah et al, 2020;Wei et al, 2019) discuss the relationship of loan growth, bank risk and profitability. Adesina (2019) suggests that asset portfolios' poor performance hampers banks' capacity to make loans.…”
Section: Review Of Literaturementioning
confidence: 99%
See 1 more Smart Citation
“…As a result of mergers, rising banks combine more and hence have lower returns. Some recent developments in this area of literature (Adesina, 2019;Aysan and Disli, 2019;Bustamante et al, 2019;Dang, 2019;Jiang et al, 2020;Nguyen & Dang, 2020;Sobarsyah et al, 2020;Wei et al, 2019) discuss the relationship of loan growth, bank risk and profitability. Adesina (2019) suggests that asset portfolios' poor performance hampers banks' capacity to make loans.…”
Section: Review Of Literaturementioning
confidence: 99%
“…An investigation by Wei et al (2019) on a panel dataset of 507 banks from four central euro area countries (France, Germany, Italy, and Spain) from 2005 to 2017 reveals that Economic policy uncertainty (EPU) has a positive effect on NPLs. However, this effect is considerably moderated by greater bank concentration.…”
Section: Review Of Literaturementioning
confidence: 99%
“…The third paper, by Wei et al (2019), is equally as important because it demonstrates how new computer-based research methods are useful in developing insights into qualitative data that was not previously possible. For example, qualitative data analysis software, such as NVivo, has been around for many years, but relies on hours of coding and reading based upon the subjective analysis of the researcher (Bazeley and Jackson, 2013).…”
Section: Methodologicalmentioning
confidence: 99%
“…While it is still possible to develop metrics for reliability and validity such as Krippendorff's alpha, this type of analysis is based on comparing the results of human analysis, on relatively small amounts of data (Hayes and Krippendorff, 2007;Krippendorff, 2013). What Wei et al (2019) demonstrate is that it is possible to use software to analyse considerably large amounts of data and produce insights not previously possible.…”
Section: Methodologicalmentioning
confidence: 99%
“… 49 Researchers pull out financial statements from the data repository and then predict financial misconduct through text analysis. 30 , 50 , 51 …”
Section: Financial Fraud Detection Data Evolutionmentioning
confidence: 99%