Systemic Risk and Bank Networks: A Use of Knowledge Graph with ChatGPT

Ren Yuan Lyu; Ren Raw Chen; San Lin Chung; Yilu Zhou

doi:10.3390/fintech3020016

Systemic Risk and Bank Networks: A Use of Knowledge Graph with ChatGPT

Ren Yuan Lyu, Ren Raw Chen, San Lin Chung^*, Yilu Zhou

^*Corresponding author for this work

Department of Computer Science and Information Engineering

Research output: Contribution to journal › Journal Article › peer-review

Abstract

In this paper, we study the networks of financial institutions using textual data (i.e., news). We draw knowledge graphs after the textual data has been processed via various natural language processing and embedding methods, including use of the most recent version of ChatGPT (via OpenAI api). Our final graphs represent bank networks and further shed light on the systemic risk of the financial institutions. Financial news reflects live how financial institutions are connected, via graphs which provide information on conditional dependencies among the financial institutions. Our results show that in the year 2016, the chosen 22 top U.S. financial firms are not closely connected and, hence, present no systemic risk.

Original language	English
Pages (from-to)	274-301
Number of pages	28
Journal	FinTech
Volume	3
Issue number	2
DOIs	https://doi.org/10.3390/fintech3020016
State	Published - 06 2024

Bibliographical note

Publisher Copyright:
© 2024 by the authors.

Keywords

ChatGPT
bank network
knowledge graph
natural language processing
systemic risk

Access to Document

10.3390/fintech3020016

Cite this

@article{ae9e287a68744e298125915d98c63956,

title = "Systemic Risk and Bank Networks: A Use of Knowledge Graph with ChatGPT",

abstract = "In this paper, we study the networks of financial institutions using textual data (i.e., news). We draw knowledge graphs after the textual data has been processed via various natural language processing and embedding methods, including use of the most recent version of ChatGPT (via OpenAI api). Our final graphs represent bank networks and further shed light on the systemic risk of the financial institutions. Financial news reflects live how financial institutions are connected, via graphs which provide information on conditional dependencies among the financial institutions. Our results show that in the year 2016, the chosen 22 top U.S. financial firms are not closely connected and, hence, present no systemic risk.",

keywords = "ChatGPT, bank network, knowledge graph, natural language processing, systemic risk",

author = "Lyu, {Ren Yuan} and Chen, {Ren Raw} and Chung, {San Lin} and Yilu Zhou",

note = "Publisher Copyright: {\textcopyright} 2024 by the authors.",

year = "2024",

month = jun,

doi = "10.3390/fintech3020016",

language = "英语",

volume = "3",

pages = "274--301",

journal = "FinTech",

issn = "2674-1032",

publisher = "Multidisciplinary Digital Publishing Institute (MDPI)",

number = "2",

}

TY - JOUR

T1 - Systemic Risk and Bank Networks

T2 - A Use of Knowledge Graph with ChatGPT

AU - Lyu, Ren Yuan

AU - Chen, Ren Raw

AU - Chung, San Lin

AU - Zhou, Yilu

PY - 2024/6

Y1 - 2024/6

N2 - In this paper, we study the networks of financial institutions using textual data (i.e., news). We draw knowledge graphs after the textual data has been processed via various natural language processing and embedding methods, including use of the most recent version of ChatGPT (via OpenAI api). Our final graphs represent bank networks and further shed light on the systemic risk of the financial institutions. Financial news reflects live how financial institutions are connected, via graphs which provide information on conditional dependencies among the financial institutions. Our results show that in the year 2016, the chosen 22 top U.S. financial firms are not closely connected and, hence, present no systemic risk.

AB - In this paper, we study the networks of financial institutions using textual data (i.e., news). We draw knowledge graphs after the textual data has been processed via various natural language processing and embedding methods, including use of the most recent version of ChatGPT (via OpenAI api). Our final graphs represent bank networks and further shed light on the systemic risk of the financial institutions. Financial news reflects live how financial institutions are connected, via graphs which provide information on conditional dependencies among the financial institutions. Our results show that in the year 2016, the chosen 22 top U.S. financial firms are not closely connected and, hence, present no systemic risk.

KW - ChatGPT

KW - bank network

KW - knowledge graph

KW - natural language processing

KW - systemic risk

UR - http://www.scopus.com/inward/record.url?scp=85216653155&partnerID=8YFLogxK

U2 - 10.3390/fintech3020016

DO - 10.3390/fintech3020016

M3 - 文章

AN - SCOPUS:85216653155

SN - 2674-1032

VL - 3

SP - 274

EP - 301

JO - FinTech

JF - FinTech

IS - 2

ER -

Systemic Risk and Bank Networks: A Use of Knowledge Graph with ChatGPT

Abstract

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this