Predictive Analysis of Global Risk Insights with a Focus on World Risk Index Factors

The research paper explores the complex dynamics of global risk assessment using different types of machine learning techniques focusing on the World Risk Index (WRI) as a comprehensive measure of global risk.WRI addresses the need for accurate risk assessment in the world marked by environmental, socioeconomic, and geopolitical uncertainties. Analysis and experimentation with various Machine Learning algorithms like Linear Regression, Random Forest Regression, Support Vector Regressor, and Extreme Gradient Boosting (XGBoost) ensemble method helps to identify some major key factors driving WRI and evaluates its significance. Results highlights the importance of Exposure, Vulnerability, Susceptibility, lack of coping capabilities, and lack of adaptive capacity in shaping global risk profiles. Study emphasizes the critical role of model selection and hyperparameter tuning in enhancing the prediction accuracy with XGBoost emerging as the most effective and best fit model. Insights gained from this research work helps to contribute informed decision- making, policy formulation and disaster preparedness efforts worldwide.