Artificial Intelligence Approach for Terror Attacks Prediction Through Machine Learning

Abstract

The rise of terrorism has become a global threat that affects every continent and country. Due to the complexity of the situation, and the technological developments that have occurred in the field, attacks and incidents have become more difficult to manage. To prevent these types of attacks, countries and organizations have started using various techniques such as machine learning and artificial intelligence.The goal of this paper is to create a framework that allows users to visualize the various characteristics of terrorist attacks by extracting data from the Global Terrorism database. The graph embedding process is performed by using two different methods.The coding approach was used for the non-coding model development. The data collected by the project were then fed to seven different machine learning models. These models included Random forest, KNN, adaboost, decision trees, and SVM. The classification accuracy of the two methods was estimated to be around 90%.