Multi-Source Data-Driven Financial Fraud Risk Analysis

In recent years, big financial fraud events occurred frequently in the world, which seriously threatened the stability of the financial system and affected the healthy development of the capital market. In particular, the ongoing COVID-19 pandemic brings unexpected economic downturn, and accelerates digital transformation, leading to more numerous and complicated financial fraud activities. For example, the information asymmetry brought about by remote businesses increases the possibility of cyber risk and induces more fraudsters to commit fraud through easier online channels.

Existing literature has done good research on the identification, analysis, and measurement of financial fraud risk based on structured quantitative data. However, the quantitative data only contain limited information, so it is difficult to break through the bottleneck under incomplete information. The advent of the information age has brought us a huge amount of multi-source data, such as news reports, images, videos, financial analysts’ reports, and textual risk disclosures in financial statements. These big data contain a wealth of risk information, which can be used as an effective supplement to traditional quantitative data. Based on the comprehensive information from multi-source data, a more effective and accurate fraud risk analysis is expected.

Big data has the typical characteristics of massiveness, multi-source, and heterogeneousness. How to obtain and deal with fraud-related big data? How to gather and fuse these multi-source data? How to extract the key risk information from multi-source data? How to use advanced technology for better financial fraud analysis? Especially, the current COVID pandemic results in new risks and new characteristics for financial fraud. What types of new data and new methods can be used to better identify and analyze financial fraud? This special issue intends to collect fraud risk analysis papers based on multi-source data, to promote in-depth exchanges among scholars, practitioners, and regulators in this field.

Potential topics include, but are not limited to:

• Fraud risk analysis with multi-source data/big data

• Fraud risk analysis with artificial intelligence (AI) methods, such as graph neural networks, deep learning, knowledge graph analysis, and machine learning

• Fraud risk analysis in typical scenarios, such as credit fraud, money laundering, insurance fraud, financial statement fraud, etc.

• Credit rating and scoring

• Big data analysis and text mining methods in financial risk analysis

• Multi-source data integration and fusion

• Risk information extraction

• Cyber risk identification and management

Manuscript submission information:

The Journal’s submission system will be open for submissions for the Special Issue ‘Multi-Source Data-Driven Financial Fraud Risk Analysis’. When submitting your manuscript please select the article type “VSI: Financial fraud analysis”. Please submit your manuscript before 31st August 2023.

All submissions deemed suitable to be sent for peer review will be reviewed by at least two independent reviewers.

Please ensure you read the Guide for Authors before writing your manuscript.

The Guide for Authors: https://www.elsevier.com/journals/emerging-markets-review/1566-0141/guide-for-authors 

The link to submit your manuscript is available on the Journal’s homepage at: https://www.editorialmanager.com/ememar/default2.aspx 

Inquiries, including questions about appropriate topics, may be sent electronically to ememar@elsevier.com 

期刊主页：https://www.sciencedirect.com/journal/emerging-markets-review