Risk identification method based on complex network analysis

Abstract

The invention provides a risk identification method based on complex network analysis, and the method comprises the steps: A, finding out all nodes which need to judge the risk conditions, and building a time sequence feature for each node; b, calculating the correlation of every two points in all the nodes, establishing a risk backbone network according to the correlation result, and calculatingindexes such as network topology characteristics; c, performing classification prediction on risk events by adopting a machine learning related method based on the risk backbone network characteristics obtained in the previous step. Risk identification based on complex network analysis is completed through the above three steps. The method is high in universality, high in objectivity and easy to operate, and the problem that risks in life are difficult to measure and evaluate objectively is solved.

Description

Technical field [0001] The present invention proposes a risk identification method based on complex network analysis, which involves risk identification, network science and other technical fields. Background technique [0002] Risk refers to the possibility or uncertainty of a certain loss or undesired result in a certain time period or point in a certain environment. Risk is an objective existence, and the loss caused by the occurrence of risk can be prevented or reduced by adopting preventive measures, but the risk cannot be eliminated. [0003] Risks are common in all areas of life. For example, fishermen in the maritime industry may encounter the risk of empty hunting and ship overturning due to bad weather and other reasons when they go fishing. In the financial industry, there is also the risk that investors cannot recover their principal when buying stocks and other products. ; Even ordinary people may encounter risks brought by disasters in their lives, such as earthquak...

AI Technical Summary

Problems solved by technology

[0010] The present invention is mainly used to solve the problem of risk identification under the background of complex systems and network structures. Most of the existing methods use risk diffusion analysis based on epidemic diseases, risk propagation threshold analysis based on network topology, and cascading failure-based Risk propagation process analysis, and these methods do not correlate and compare the characteristics of the system at each time period or time point, and lack time dynamic characteristics

Images