Trend and Identification Analysis of Anti-investigation Behavior in Crime by Machine Learning Fusion Algorithm

Abstract

In recent years, people’s living standards have gradually improved, and informatization has brought convenience, but it has also led to many criminal cases. Because the criminals’ criminal methods are diverse and constantly renovated, this feature is very prominent, and the illegal activities on the Internet are becoming more and more intense. Therefore, it is necessary to strengthen the research on the trend and identification of anti-investigation behavior in crime. The purpose of this paper is to study how to use machine learning fusion algorithms in the trend and identification of anti-investigation behavior in crime. This paper proposes a machine learning fusion algorithm and the basic conceptual knowledge of anti-investigation behavior in crime. The experimental results of this paper show that with the increasing number of criminal incidents, criminals’ means of committing crimes have also been improved. The anti-investigation capabilities of criminals have also become more sophisticated, which makes the work of law enforcement officers more difficult. The anti-investigation behavior of criminals in crime has many characteristics, among which the concealment reaches 54%-68%, and the virtuality reaches 68%-79%. It can be seen that the characteristics of criminals’ anti-investigation behavior provide a wider space for criminals to commit crimes. The advantage of the machine fusion algorithm is that the classification rules generated are easy to understand and have high accuracy, so it is very suitable for the classification and identification of anti-investigation behaviors in crimes. Therefore, it is urgent to use machine fusion algorithms to identify them.