Data-Driven Intervention Strategies for Mitigating Illegal Wildlife Trade: A Case Study of the United States

Given the escalating threat posed by illegal wildlife trade to global biodiversity and ecological equilibrium, this study endeavors to forecast the potential effects of a five-year, data-driven initiative on curbing illicit wildlife trade within the United States over the forthcoming half-decade. This paper establishes a complete system of evaluation indicators to assess the progress of the program, and establishes a system dynamics model based on Vensim modeling and simulation to predict a 14% increase in law enforcement after the implementation of the data-driven program. A weighted optimization model with ARMA and multiple linear regression weights was established to predict the volume of illegal wildlife trade in the next five to ten years with or without intervention, the weighted prediction model underwent optimization using the particle swarm algorithm, resulting in enhanced convergence speed and accuracy of the model’s solution.