Wildlife Development Prediction Based on Big Data and Bayesian Logistic Regression

Illegal trade in wildlife poses a serious threat to global biodiversity and ecological balance, and measures to protect it are urgently needed. In this paper, data collection was conducted, key indicators were introduced, multifaceted data from different countries were integrated for evaluation, and the weights of the indicators were calculated using the entropy weighting method to screen out ideal collaborators for wildlife conservation programmes. Data-driven analyses were then used to demonstrate the importance of the collaborators in combating illegal trade and the appropriateness of this paper's programme. Afterwards the paper developed a system dynamics model to estimate the parameter magnitudes and observed the trend graphs. Finally a logistic logistic regression model based on a Bayesian approach was developed to estimate the parameters and the results show that the model proves the high feasibility of the project.