Empty-shell enterprise identification method, device and equipment and computer storage medium

Abstract

The invention discloses an empty-shell enterprise identification method, device and equipment and a computer storage medium. According to the technical scheme, the method comprises the steps of obtaining industrial and commercial registration information of a to-be-identified enterprise, obtaining enterprise information risk index data of the to-be-identified enterprise based on the industrial and commercial registration information, and inputting the enterprise information risk index data into an empty shell enterprise identification model to obtain a score of the to-be-identified enterprise, the empty-shell enterprise identification model is constructed according to the information risk index of the empty-shell enterprise, and determining whether the to-be-identified enterprise is the empty-shell enterprise according to the score. According to the embodiment of the invention, whether the to-be-identified enterprise is an empty shell enterprise or not can be effectively identified, manual operation and manual auditing are not needed, and risks caused by manual processing are avoided; empty shell enterprise samples and non-empty shell enterprise samples do not need to be manually labeled, so that a large amount of time and manpower are saved; and the problem of insufficient classification reliability caused by fuzzy positive and negative sample boundaries, non-uniform sample distribution and the like is avoided.

Description

technical field [0001] The application belongs to the field of network information technology, and in particular relates to a method, device, equipment and computer storage medium for identifying a shell enterprise. Background technique [0002] A shell business is usually a legal entity with no physical operations or assets and is often used to conceal illegal financial activities. At present, there is still no unified identification standard for shell companies in my country, so it is particularly important to use data-driven and technology-enabled methods to conduct verification before opening a corporate account. [0003] The existing common identification methods for shell companies mainly include: manual investigation by professionals of financial institutions and the use of machine learning modeling methods to establish models by analyzing various data indicators of enterprises and then evaluate the risks of shell companies. Machine learning methods Including supervi...

AI Technical Summary

Problems solved by technology

[0004] The existing methods for identifying shell companies, manual investigation is time-consuming and labor-intensive, and the efficiency is low, and there is a risk that the manual prevention and control measures will fail due to the fact that professionals are driven by interests

Supervised learning requires a lot of labeling of empty shells and non-empty shells of enterprises, and the labeling process also consumes a lot of time and manpower

Unsupervised learning has insufficient classification reliability due to problems such as blurred positive and negative sample boundaries and uneven sample distribution.

Images