Financial investment risk prediction under the application of information interaction Firefly Algorithm combined with Graph Convolutional Network

Muyang Li

PLOS ONE, 2023, vol. 18, issue 9, 1-18

Abstract: This paper improves the performance of the model by Graph Convolutional Network (GCN) and Firefly Algorithm (FA) to optimize the financial investment risk prediction model. It studies the application of GCN in financial investment risk prediction model and elaborates on the role of FA in the model. To further improve the accuracy of the prediction model, this paper optimizes and improves the FA and verifies the effectiveness of the optimized model through experiments. Experimental results show that the optimized model performs well in feature selection, and the optimal accuracy of feature selection reaches 91.9%, which is much higher than that of traditional models. Meanwhile, in the analysis of the number of iterations of the model, the performance of the optimized algorithm gradually tends to be stable. When the number of iterations is 30, the optimal value is found. In the simulation experiment, when an unexpected accident occurs, the prediction accuracy of the model decreases, but the prediction performance of the optimized algorithm proposed here is significantly higher than that of the traditional model. In conclusion, the optimized model has high accuracy and reliability in financial investment risk prediction, which provides strong support for financial investment decision-making. This paper has certain reference significance for the optimization of financial investment risk prediction model.

Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0291510 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 91510&type=printable (application/pdf)

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:plo:pone00:0291510

DOI: 10.1371/journal.pone.0291510

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().