Assessing Geopolitical Risks and Their Economic Impact on the USA Using Data Analytics

Abstract

Understanding geopolitical risks is a paramount aspect of examining the stability and resilience of national economies, specifically in today’s rapidly evolving global surroundings. Advanced analytics in the big data era open unparalleled avenues toward the quantification and comprehension of geopolitical risks on the performance of the economy of the United States. The prime objective of this study was to analyze the impact of geopolitical events on the U.S. economy, to identify key risk factors and their economic implications as well as propose strategies for mitigating adverse effects. Datasets used in this exploration were collected from different reliable sources to assess sources of geopolitical risk data and their economic impact on the U.S. First, data on geopolitical risk were collated from a combination of real-time news reports, government databases, and international organizations involved in monitoring geopolitical events. Key sources for this included GDELT news and sentiment data, official reports from U.S. government agencies such as the Department of State and the Department of Defense about foreign policy, conflict, and security, while major financial news outlets like Bloomberg and Reuters provided moment-by-moment coverage of events in the geopolitical sphere. We applied the Geo-Risk-Regressor model, a form of multimodal design to predict geopolitical threats arising from economic indicators, real-time news sentiment, and government reports on geopolitical events. The Geo-Risk-Regression Model is an integrated set of machine learning algorithms, from time-series and NLP to econometric regression, on structured and unstructured data comprising economic indicators, real-time news sentiment, and government reports on geopolitical events. A rigorous structured procedure was followed in implementing the Geo-Risk-Regressor to analyze the economic impact of geopolitical risks in the U.S. To assess and evaluate the performance of the algorithms, two key performance evaluation metrics were utilized MSE & R-squared. Among all the models, the best performance was that of XG-Boost; it had the lowest MSE and highest R². Thus, XG-Boost is the best model fitted for the prediction of GPRD_THREAT, probably because of its robust optimization and also its capability to capture a lot of complicated patterns in data. The geopolitical threat level perceived using the proposed models will enable business organizations in the USA to identify and manage risks that may affect the operations of the business organizations. Companies can, therefore, understand factors that contribute to risk and develop contingency plans, enabling them to take proactive measures to mitigate negative impacts from geopolitical events. Predictive models will help businesses in America estimate the potential risks to their supply chains and create strategies for mitigating any disruptions that might come through geopolitical events.