NORMA eResearch @NCI Library

Analysis and Prediction of Terrorist Attacks using Supervised Machine Learning and Deep Learning Techniques

Jyothilinga, Sinchana (2023) Analysis and Prediction of Terrorist Attacks using Supervised Machine Learning and Deep Learning Techniques. Masters thesis, Dublin, National College of Ireland.

[thumbnail of Master of Science]
PDF (Master of Science)
Download (2MB) | Preview
[thumbnail of Configuration manual]
PDF (Configuration manual)
Download (1MB) | Preview


Terrorism has been a major concern worldwide for a very long time. There have been thousands of civilian casualties as a result of these assaults. If these assaults could be foreseen, then governments and their defense establishments can work together to devise a plan of action to prevent them. This is achievable with the use of machine learning. This study proposes to analyze the historical terrorist attack data available in the Global Terrorism Database (GTD) to forecast the future terrorist attacks and fatalities of the top three most attacked nations and also classify the attack weapon type and the terrorist group responsible for the attack. The dataset was preprocessed by converting relevant variables to categorical form, filling the missing values with Mean/Median imputation, and shortening lengthier categorical names. Weapons were classified using a kNN classifier, perpetrators were categorized using Decision Tree and MLPClassifiers, and fatality predictions were made using Random Forest and MLPRegressors. Time Series Analysis using FbProphet model was used to forecast terrorist strikes in the top three most attacked countries. The kNN classifier yielded an accuracy of 92.25%. For perpetrator classification, both the Decision Tree classifier and MLPClassifier performed equally well, providing an accuracy of 90%. The Random Forest regressor outperformed the MLPRegressor obtaining a lower MSE value. The forecasts of the terrorist attacks in 2021 seen in the plots obtained by time series analysis match with the actual attacks that happened during that year. ML offers a large potential for an investigation into terrorism to precisely anticipate future attacks.

Item Type: Thesis (Masters)
Muntean, Cristina Hava
Subjects: H Social Sciences > HV Social pathology. Social and public welfare
Q Science > QA Mathematics > Electronic computers. Computer science
T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science
Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions: School of Computing > Master of Science in Data Analytics
Depositing User: Tamara Malone
Date Deposited: 19 May 2023 13:58
Last Modified: 19 May 2023 13:58

Actions (login required)

View Item View Item