Illegal wildlife trade measuring based on data-driven analyses

Abstract

Illegal wildlife trade (IWT) stands as a silent yet devastating force. In this paper a 5-year project is proposed to have a measurable impact on reducing the illicit trade based on data-driven analyses. First, we develop the Client Performance Evaluation Model to identify the ideal client. Secondly, the AI-Powered Wildlife Guardian Project (AWGP) is designed to monitor and manage the IWT chain, from supply to demand. Additional powers and resources for the project’s success are identified. The C4ADS Air Seizure Database highlights China’s need for the authority for cross-border monitoring and enforcement. The Impact Prediction Model (IPM) is crafted using time-series analysis to predict the effects of the project on illegal wildlife trade. Initially, there were 41 seizures in 2023, with an expected rise to 104 by 2028 without intervention. A probability analysis is conducted to determine the likelihood of achieving the goal of reducing illegal wildlife trade by 50%. Finally, a probability analysis is conducted to determine the likelihood of achieving the goal of reducing illegal wildlife trade by 50%.