Multidimensional Knowledge Graph Embeddings for International Trade Flow Analysis

TL;DR

This work implements KonecoKG, a knowledge graph representation of economic trade data with multidimensional relationships with multidimensional relationships using SDM-RDFizer, and transforms the relationships into a knowledge graph embedding using AmpliGraph to predict international trade 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.

Figures (5)

• Figure 1: Log density of bilateral trade flows across time
• Figure 2: Trade flow prediction and analysis pipeline
• Figure 3: KonecoKG data model diagram
• Figure 4: Sample trade network in KonecoKG
• Figure 5: Comparison of predictions (on log-log scale)