Terrorism Risk Prediction Model Based on Support Vector Machine Optimized by Whale Algorithm

To realize the short-term prediction of regional terrorism risk index, this paper proposes a terrorism risk prediction model based on support vector machine (SVM) optimized by whale optimization algorithm (WOA). WOA is used to select penalty parameter and kernel function parameter of SVM. The model takes 16 typical quantitative indicators as independent variables. And the Global Terrorist Index (GTI) of the World Economic and Peace Research Institute is used as the output of the prediction model. The simulation experiments are carried out with the data of Asian countries from 2008 to 2018, and the prediction results are compared with those of BP neural network, traditional SVM model and particle swarm optimization SVM model. The experimental results show that the terrorism risk prediction model based on WOA-SVM has higher prediction accuracy, more stable prediction performance, and can effectively realize the prediction of terrorist risk index.