Predicting Terrorist Attacks in Afghanistan Using Generalized Multivariate Regression and Time Series Analysis
CSEF · 2018 Computational Systems & Analysis
Overview
Objectives/Goals The objective of this study is to help prevent terrorist attacks in one of the provinces of Afghanistan by discovering the factors that significantly affect the rate at which terrorist attacks occur, and then by using that data to predict terrorist attacks. Methods/Materials Laptop computer with RStudio installed. Used data from the United Nations and the Afghan government to create a generalized linear model, ran a time series analysis which generated predictions of future terrorist attacks in Afghanistan. Results From the generalized linear model I created, I determined that opium production had by far the strongest correlation to terrorist attacks in Afghanistan out of the nearly 40 covariates I analyzed. I was also able to predict through a time series analysis, that there will be 39, 36, and 42 terrorist attacks respectively in the next three years in the capital of Afghanistan. Conclusions/Discussion One way to reduce the number of terrorist attacks in Afghanistan could be to limit the production of opium. Resources, both preventative and retaliatory, can be allocated to regions based on the number of attacks predicted.
Summary statement
I created a prediction of terrorist attacks in Afghanistan using generalized multivariate regression and time series analysis.
Help received
I learned the statistical procedures necessary for this project through independent study as well as explanations from Mihnea Andrei, a graduate student at the UCSB Department of Statistics. I used data from the U.N. and the Afghan Govt.
Competition history
- CSEF 2018
Resources
Related projects
CSEF · 2016
Predicting and Identifying Forced Human Displacement Hotspots Using Multiple Linear Regression and Neural Networks
ISEF · 2019
An Intelligent Security System for High-Terrorism-Risk Cities: Real-Time Prediction, Weapon Detection and Instant Solution (ISTC)
CSEF · 2014
Improving Algorithms for the Optimal Allocation of Security Resources, Year 2
CSEF · 2017
A Machine-Learning Approach to Correlate Environmental and Demographic Factors to Cancer Incidences across US Counties
CSEF · 2018
A Data Analysis Approach to Wildfire Prediction
ISEF · 2020
An Enhanced Early Detection Model of Dengue Fever Outbreaks Using SEIR Infectious Disease Epidemiological Compartments, Generalized Linear Regression, and Statistical Computing
CSEF · 2017
Developing a Predictive Model for On-Campus Crime Using Machine Learning Algorithms and Reporting via Mobile App
ISEF · 2020
A Machine Learning Approach to Identify Socio-economic Factors Responsible for Patients Dropping Out of Substance Abuse Treatment
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects