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

EasyChair Preprint 13978

Abstract

The illegal wildlife trade is threatening global species diversity. To address this challenge, we have developed a five-year data-driven plan and explored its impact on the illegal wildlife trade. Firstly, we proposed a method to find target customers based on big data and found that the $U.S.$ appears frequently in relevant studies. Secondly, we justify the selection of the $U.S.$ government as the client based on published literature research. Thirdly, we identified the need for the client to consider domestic claims and energy-related electricity when implementing the project, based on the description of the three Level 1 indicators in the United States Statistical Yearbook. Lastly, we built a weighted optimization prediction model based on linear regression. Under the assumptions of the model, we find that even in the face of a small-scale contingency , the system is still able to maintain stability and largely achieve the desired goals.

Keyphrases: Weighted optimization prediction, evaluation index system, illegal wildlife trade, particle swarm algorithm

@booklet{EasyChair:13978,
  author    = {Pan Xue and Tianchang Zhou and Hui Sun and Jihao Song and Xiaoliang Guo and Zhiwei Shao},
  title     = {Data-Driven Intervention Strategies for Mitigating Illegal Wildlife Trade: a Case Study of the United States},
  howpublished = {EasyChair Preprint 13978},
  year      = {EasyChair, 2024}}