Political, Economic and Military (PEM) Framework for Reciprocal Tariff Based on Machine Learning

A Novel Approach

Abstract

The unprecedented escalation of reciprocal tariffs between global superpowers has redefined the silhouette of modern trade diplomacy. This study employs a deep learning algorithm to identify the evolving nodes of non-conditioned long-term consequences of the retaliatory tariff policies in the US-China trade war, serving as a primary case study. The results of the study determine the impact of reciprocal tariff shaping trends on Political, Economic, and Military (PEM) facets of the modern world, which collectively shape the future of humankind. The analysis of trade data, macroeconomic indicators, and international sentiment patterns through Google Trends from 01/01/2024 to 04/09/2025 reveals how protectionist measures can lead to new constructionist dynamics in the political, economic, and military scenarios amid volatile, changing landscapes. The study leads to detailing the existence of such clusters in the PEM framework. The metaphor of “gradual and nonlinear’ has been used to demonstrate the often creeping, often nonlinear nature of these long-term impacts. Furthermore, the LDA method in topic modelling has been deployed to identify sentiments on the political, economic, and military impact of reciprocal tariffs on the global economy.