Quantitative Analysis and Prediction of Global Terrorist Attacks Based on Machine Learning

Abstract

Terrorist attacks pose a great threat to global security, and their analysis and prediction are imperative. Considering the high frequency of terrorist attacks and the inherent difficulty in finding related terrorist organizations, we propose a classification framework based on ensemble learning for classifying and predicting terrorist organizations. The framework includes data preprocessing, data splitting, five classifier prediction models, and model evaluation. Based on a quantitative statistical analysis of terrorist organization activities in GTD from 1970 to 2017 and feature selection using the SelectKBest method in scikit learn, we constructed five classification and prediction models of terrorist organizations, namely, decision tree, bagging, random forest, extra tree, and XGBoost, and utilized a 10-fold cross-validation method to verify the performance and stability of the proposed model. Experimental results showed that the five models achieved excellent performance. The XGBoost and random forest models achieved the best accuracies (97.16% and 96.82%, respectively) of predicting 32 terrorist organizations with the highest attack frequencies. The proposed classifier framework is useful for the accurate and efficient prediction of terrorist organizations responsible for attacks and can be extended to predict all terrorist organizations.