An evaluation of the effectiveness of three early-warning models on financial indexes

ABSTRACT

In this paper, we construct three financial early warning models, and evaluate and compare their early warning effects. These models are based on factor analysis, logistic regression, and Verhulst-BP neural network, taking Chinese listed mineral resource companies as samples. The results show that the model based on Verhulst-BP neural network has the best early warning effect among the three models, and the early warning model based on logistic regression is more accurate than the one based on factor analysis.

KEYWORDS:

• Verhulst-BP neural network
• factor analysis
• logistic regression
• financial early-warning model
• evaluation

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

This paper is supported by the Science and Technology Plan Project of Sichuan Province (2020JDR0230), the Research and Innovation Team Construction Programme of Sichuan Provincial Universities (18TD016), and the foundation of the System Science and Enterprise Development Research Center of Sichuan Province (Xq16C11).