Smart Natural Disaster Relief: Assisting Victims with Artificial Intelligence in Lending

Yidi Liu; Xin Li; Zhiqiang (Eric) Zheng

doi:10.1287/isre.2023.1230

Smart Natural Disaster Relief: Assisting Victims with Artificial Intelligence in Lending

Yidi Liu^*, Xin Li^*, Zhiqiang (Eric) Zheng^*

^*Corresponding author for this work

Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review

18 Citations (Scopus)

575 Downloads (CityUHK Scholars)

Abstract

Natural disasters wreak economic havoc and cause financial distress for victims. Commercial loans provided by lending firms play a key role in helping victims recover from disasters. This research note studies whether lenders' use of artificial intelligence (AI) in the lending process can, through reducing delinquency, benefit borrowers who experience natural disasters. Collaborating with a leading credit-scoring company, we track borrowers' loan applications and lenders' use of customized AI solutions in assessing loan risks. We find that borrowers who apply to AI-empowered lenders fare better in reducing delinquency rates after experiencing natural disasters. Notably, such a disaster mitigation effect is more pronounced for borrowers with lower credit scores. We explore the possible mechanisms at play and discuss the implications of our findings. © 2023 INFORMS

Original language	English
Pages (from-to)	489-504
Journal	Information Systems Research
Volume	35
Issue number	2
Online published	31 May 2023
DOIs	https://doi.org/10.1287/isre.2023.1230
Publication status	Published - Jun 2024

Bibliographical note

Information for this record is supplemented by the author(s) concerned.

Funding

The authors thank the guest editors of the special issue, associate editor, and the reviewers for their invaluable comments and suggestions. The authors also thank the anonymous company “X” that allowed us access the data for the study. The research is partially supported by the Research Grants Council of the Hong Kong Special Administrative Region, China [GRF 11501722, 11500519]; the City University of Hong Kong [SRG 7005474, 7005767], the InnoHK initiative, the Government of the HKSAR, and Laboratory for AI-Powered Financial Technologies.

Research Keywords

AI
natural disasters
lending
delinquency
credit scoring
fintech
CREDIT
RISK
INFORMATION
EXPERIENCE
DEFAULT

Publisher's Copyright Statement

COPYRIGHT TERMS OF DEPOSITED POSTPRINT FILE: © 2023, INFORMS. This is the author accepted manuscript (AAM) of a paper published in Information Systems Research. The final published version of record is available online at: https://doi.org/10.1287/isre.2023.1230. Yidi Liu, Xin Li, Zhiqiang (Eric) Zheng (2023) Smart Natural Disaster Relief: Assisting Victims with Artificial Intelligence in Lending. Information Systems Research.

RGC Funding Information

RGC-funded

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access Output

10.1287/isre.2023.1230

144850865.pdfPost-print, 1 MB

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@article{359f77418b0145be9ee3a1ae22e27e4f,

title = "Smart Natural Disaster Relief: Assisting Victims with Artificial Intelligence in Lending",

abstract = "Natural disasters wreak economic havoc and cause financial distress for victims. Commercial loans provided by lending firms play a key role in helping victims recover from disasters. This research note studies whether lenders' use of artificial intelligence (AI) in the lending process can, through reducing delinquency, benefit borrowers who experience natural disasters. Collaborating with a leading credit-scoring company, we track borrowers' loan applications and lenders' use of customized AI solutions in assessing loan risks. We find that borrowers who apply to AI-empowered lenders fare better in reducing delinquency rates after experiencing natural disasters. Notably, such a disaster mitigation effect is more pronounced for borrowers with lower credit scores. We explore the possible mechanisms at play and discuss the implications of our findings. {\textcopyright} 2023 INFORMS",

keywords = "AI, natural disasters, lending, delinquency, credit scoring, fintech, CREDIT, RISK, INFORMATION, EXPERIENCE, DEFAULT",

author = "Yidi Liu and Xin Li and Zheng, {Zhiqiang (Eric)}",

note = "Information for this record is supplemented by the author(s) concerned.",

year = "2024",

month = jun,

doi = "10.1287/isre.2023.1230",

language = "English",

volume = "35",

pages = "489--504",

journal = "Information Systems Research",

issn = "1047-7047",

publisher = "Institute for Operations Research and the Management Sciences (INFORMS)",

number = "2",

}

TY - JOUR

T1 - Smart Natural Disaster Relief

T2 - Assisting Victims with Artificial Intelligence in Lending

AU - Liu, Yidi

AU - Li, Xin

AU - Zheng, Zhiqiang (Eric)

N1 - Information for this record is supplemented by the author(s) concerned.

PY - 2024/6

Y1 - 2024/6

N2 - Natural disasters wreak economic havoc and cause financial distress for victims. Commercial loans provided by lending firms play a key role in helping victims recover from disasters. This research note studies whether lenders' use of artificial intelligence (AI) in the lending process can, through reducing delinquency, benefit borrowers who experience natural disasters. Collaborating with a leading credit-scoring company, we track borrowers' loan applications and lenders' use of customized AI solutions in assessing loan risks. We find that borrowers who apply to AI-empowered lenders fare better in reducing delinquency rates after experiencing natural disasters. Notably, such a disaster mitigation effect is more pronounced for borrowers with lower credit scores. We explore the possible mechanisms at play and discuss the implications of our findings. © 2023 INFORMS

AB - Natural disasters wreak economic havoc and cause financial distress for victims. Commercial loans provided by lending firms play a key role in helping victims recover from disasters. This research note studies whether lenders' use of artificial intelligence (AI) in the lending process can, through reducing delinquency, benefit borrowers who experience natural disasters. Collaborating with a leading credit-scoring company, we track borrowers' loan applications and lenders' use of customized AI solutions in assessing loan risks. We find that borrowers who apply to AI-empowered lenders fare better in reducing delinquency rates after experiencing natural disasters. Notably, such a disaster mitigation effect is more pronounced for borrowers with lower credit scores. We explore the possible mechanisms at play and discuss the implications of our findings. © 2023 INFORMS

KW - AI

KW - natural disasters

KW - lending

KW - delinquency

KW - credit scoring

KW - fintech

KW - CREDIT

KW - RISK

KW - INFORMATION

KW - EXPERIENCE

KW - DEFAULT

UR - http://gateway.isiknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcAuth=LinksAMR&SrcApp=PARTNER_APP&DestLinkType=FullRecord&DestApp=WOS&KeyUT=001001859100001

U2 - 10.1287/isre.2023.1230

DO - 10.1287/isre.2023.1230

M3 - RGC 21 - Publication in refereed journal

SN - 1047-7047

VL - 35

SP - 489

EP - 504

JO - Information Systems Research

JF - Information Systems Research

IS - 2

ER -

Smart Natural Disaster Relief: Assisting Victims with Artificial Intelligence in Lending

Abstract

Bibliographical note

Funding

Research Keywords

Publisher's Copyright Statement

RGC Funding Information

UN SDGs

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

GRF: Personalized Customer Engagement Considering User Blocking of Individualized Communication Channels

GRF: Online Information-aided Pricing: Toward Deeper Understanding of Signals in Unstructured Data

Cite this

Smart Natural Disaster Relief: Assisting Victims with Artificial Intelligence in Lending

Abstract

Bibliographical note

Funding

Research Keywords

Publisher's Copyright Statement

RGC Funding Information

UN SDGs

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Projects

GRF: Personalized Customer Engagement Considering User Blocking of Individualized Communication Channels

GRF: Online Information-aided Pricing: Toward Deeper Understanding of Signals in Unstructured Data

Cite this