This project analyzes over 200,000 terrorist incidents recorded between 1970 and 2020 using Python, SQL, SQLite, and Power BI.
The objective was to transform raw terrorism incident data into actionable intelligence through data cleaning, feature engineering, exploratory analysis, geospatial intelligence, SQL analytics, and interactive dashboard development.
This project demonstrates an end-to-end analytics workflow, from raw data processing to executive-level intelligence reporting.
- Python
- Pandas
- NumPy
- Matplotlib
- Seaborn
- SQLite
- SQL
- Power BI
- Jupyter Notebook
- Missing value treatment
- Data standardization
- Date formatting
- Feature creation
Created analytical features including:
- Casualties
- Attack Success
- Suicide Attack Indicator
- Decade
- High Casualty Incidents
Analyzed:
- Incident trends over time
- Geographic distribution
- Attack methods
- Weapon types
- Target sectors
- Terrorist group activity
Performed:
- Correlation analysis
- Decade-based trend analysis
- High-casualty incident analysis
- Fatality analysis
- Group activity analysis
Analyzed:
- Terrorism hotspots
- Regional distribution
- City-level incident concentration
- Geographic patterns
Built a SQLite database and executed intelligence-focused SQL queries including:
- Top affected countries
- Most active groups
- Deadliest organizations
- Regional fatality analysis
- Historical trend analysis
Created an interactive Power BI dashboard consisting of:
- Executive Overview
- Geographic Intelligence
- Attack Analysis
- Organization Analysis
- Casualty Analysis
- Historical Trends
- Intelligence Summary
global-terrorism-intelligence-analytics
│
├── notebooks
│ ├── 01_data_cleaning.ipynb
│ ├── 02_feature_engineering_and_eda.ipynb
│ ├── 03_advanced_intelligence_analytics.ipynb
│ ├── 04_geospatial_intelligence.ipynb
│ └── 05_sql_database_creation.ipynb
│
├── screenshots
│
├── sql
│ └── intelligence_queries.sql
│
├──.gitignore
│
├── README.md
│
└── requirements.txt
Provides a high-level summary of terrorism incidents, fatalities, affected countries, and regional distribution.
Highlights regional hotspots, city-level concentration of incidents, and geographic distribution patterns.
Examines:
- Most common attack methods
- Weapon types used
- Target sectors
- Attack patterns
Identifies:
- Most active terrorist groups
- Deadliest organizations
- Organizational activity trends
Analyzes:
- Fatalities by country
- Suicide attacks
- Attack success rates
- High-casualty incidents
Shows how terrorism activity evolved over time and identifies periods of increased activity.
Provides an executive briefing highlighting key intelligence findings from the analysis.
- Iraq experienced the highest number of terrorist incidents.
- The Taliban emerged as the most active and deadliest terrorist organization.
- Bombings and explosions represented the most common attack method.
- Explosives were the most frequently used weapon type.
- Private Citizens & Property were the most frequently targeted sector.
- The Middle East & North Africa recorded the highest number of fatalities.
- Terrorism activity peaked during the mid-2010s.
- Exploratory Data Analysis (EDA)
- Statistical Analysis
- Trend Analysis
- Intelligence Analysis
- Data Cleaning
- Feature Engineering
- Data Transformation
- Database Creation
- Query Writing
- Aggregations
- Filtering
- Ranking
- Trend Analysis
- Matplotlib
- Seaborn
- Power BI
- Dashboard Design
The Global Terrorism Database (GTD), SQLite database, and Power BI dashboard file are excluded from this repository due to file size limitations and data licensing considerations.
The complete dataset can be obtained from START (National Consortium for the Study of Terrorism and Responses to Terrorism). https://www.start.umd.edu/data-tools/GTD
Screenshots and the complete analytical workflow are provided to demonstrate the project methodology and findings.
- Forecast terrorism trends using machine learning models.
- Build an interactive Streamlit application.
- Develop country-level terrorism risk scores.
- Integrate near real-time incident data sources.
- Create predictive threat intelligence dashboards.
Josiah Mathew
Data Analyst | Data Engineer | Power BI Developer | CBRNe Professional
LinkedIn: https://www.linkedin.com/in/josiah-mathew-17547628b
GitHub: https://github.com/stu99a