Identifying Fintech risk through machine learning: analyzing the Q&A text of an online loan investment platform

Huosong Xia (), Jing Liu () and Zuopeng Justin Zhang ()
Additional contact information
Huosong Xia: Wuhan Textile University
Jing Liu: Wuhan Textile University
Zuopeng Justin Zhang: University of North Florida

Annals of Operations Research, 2024, vol. 333, issue 2, No 4, 579-599

Abstract: Abstract Financial risks associated with Fintech have been increasing with its significant growth in recent years. Aiming at addressing the problem of identifying risks in online lending investment under a financial technology platform, we develop a Q&A text risk recognition model based on attention mechanism and Bi-directional Long Short-Term Memory. First, the Q&A pairing on the text data set is carried out, and the matching data set is selected for the next analysis. Secondly, the online loan investment platform is assessed by the named entity recognition of the question text. Finally, the risk level of the corresponding investment platform is evaluated based on the answer text. The experimental results show that the proposed model has achieved improved precision, recall, F1-score, and accuracy compared with other models. Our proposed model can be applied to identify the risks from the text posted on online loan investment platforms and can be used to guide investors’ investment and improve the management of financial technology platforms.

Keywords: Analytics; Attention mechanism; Bi-directional long short-term memory (BiLSTM); Fintech risk identification; Machine learning (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s10479-020-03842-y Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:annopr:v:333:y:2024:i:2:d:10.1007_s10479-020-03842-y

Ordering information: This journal article can be ordered from
http://www.springer.com/journal/10479

DOI: 10.1007/s10479-020-03842-y

Access Statistics for this article

Annals of Operations Research is currently edited by Endre Boros

More articles in Annals of Operations Research from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().