A Gradient Boosting Machine Model of Economic and Socio-Economic Determinants of Terrorism: The Northern Nigerian Perspective

This study develops a Gradient Boosting Machine (GBM) model to analyze the socio-economic indicators associated with terrorism in Northern Nigeria. The aim is to identify key economic factors influencing terror incidents and provide actionable insights for counterterrorism (CT) strategies. The methodology involves a time series dataset spanning from 1991 to 2024, incorporating variables such as unemployment rate, illiteracy rate, GDP growth, and inflation rates. The GBM model, known for its robustness in handling complex data relationships, demonstrates strong predictive capabilities, achieving an R² score of 0.8734, indicating that approximately 87.34% of the variance in terror incidents is explained by the socio-economic factors. Correlation analysis reveals significant relationships, particularly between terror incidents and unemployment (0.71) and illiteracy rates (0.79). The model forecasts a troubling increase in terror incidents from approximately 400 in 2025 to 500 by 2030, highlighting ongoing security challenges. The findings emphasize the urgent need for comprehensive CT measures that address underlying socio-economic issues. Policy makers are urged to implement job creation programs, enhance educational opportunities, and foster community engagement to mitigate the factors driving terrorism. These results underscore the importance of a multifaceted approach that combines security measures with socio-economic development to create a more stable and secure Northern Nigeria.