Data-Driven Strategies for Combating Illegal Wildlife Trade: A Predictive Analysis

In this paper, we address the challenge of illegal trafficking of multiple wildlife species worldwide and propose three major data-driven measures aimed at providing wildlife protection options to law enforcement agencies. For measure 1, taking the number of cases intercepted by law enforcement agencies each year as a measure, a BP neural network based on particle swarm optimization algorithm is established to predict the effect of the measure. The results show that measure 1 can reduce the number of cases by 15.07% in the next five years. For measure 2, the improved SIR Model is creatively applied to predict the measure. The results show that the proposed method can reduce the number of cases by 10.17%. For measure 3, a linear programming model is used to calculate the number of satellites that need to be launched by World Wide Fund for Nature (WWF), and the results show that the scheme reduces the number of cases by 15.08%.