Multidimensional Knowledge Graph Embeddings for International Trade Flow Analysis

TL;DR

This paper introduces KonecoKG, a multidimensional knowledge graph embedding approach for analyzing international trade flows, aiming to better capture complex economic data dynamics beyond traditional regression methods.

Contribution

The paper presents a novel application of knowledge graph embeddings to economic trade data, enabling improved modeling of complex, nonlinear trade relationships.

Findings

KonecoKG effectively models high-dimensional trade data.

Knowledge graph embeddings outperform traditional methods in trade prediction.

The approach captures structural changes in economic relationships.

Abstract

Understanding the complex dynamics of high-dimensional, contingent, and strongly nonlinear economic data, often shaped by multiplicative processes, poses significant challenges for traditional regression methods as such methods offer limited capacity to capture the structural changes they feature. To address this, we propose leveraging the potential of knowledge graph embeddings for economic trade data, in particular, to predict international trade relationships. We implement KonecoKG, a knowledge graph representation of economic trade data with multidimensional relationships using SDM-RDFizer, and transform the relationships into a knowledge graph embedding using AmpliGraph.