Forecasting Binary Economic Events in Modern Mercantilism: Traditional methodologies coupled with PCA and K-means Quantitative Analysis of Qualitative Sentimental Data

TL;DR

This paper introduces a novel data-driven approach combining PCA and K-means clustering on semantic embeddings from news articles to predict binary economic events related to modern mercantilism, improving interpretability and accuracy.

Contribution

It presents a scalable methodology that leverages high-dimensional text analytics to quantitatively analyze and forecast mercantilist economic dynamics.

Findings

PCA effectively reduces semantic embedding dimensions revealing key features.

Semantic features identified are strong predictors of protectionism and technological decoupling.

The approach enhances interpretability and predictive performance in economic event forecasting.

Abstract

This paper examines Modern Mercantilism, characterized by rising economic nationalism, strategic technological decoupling, and geopolitical fragmentation, as a disruptive shift from the post-1945 globalization paradigm. It applies Principal Component Analysis (PCA) to 768-dimensional SBERT-generated semantic embeddings of curated news articles to extract orthogonal latent factors that discriminate binary event outcomes linked to protectionism, technological sovereignty, and bloc realignments. Analysis of principal component loadings identifies key semantic features driving classification performance, enhancing interpretability and predictive accuracy. This methodology provides a scalable, data-driven framework for quantitatively tracking emergent mercantilist dynamics through high-dimensional text analytics