Multidimensional Knowledge Graph Embeddings for International Trade Flow Analysis

2024/10/19 by Durgesh Nandini, Simon Bloethner, Nandini, Durgesh +5 · 1 citation
Business, Management and Accounting · Computer Science · Economics, Econometrics and Finance · #Artificial Intelligence (cs.AI) #Data Mining Algorithms and Applications #FOS: Computer and information sciences #FOS: Economics and business #General Economics (econ.GN) #Global Trade and Competitiveness #Global trade and economics #Information Retrieval (cs.IR) #Machine Learning (cs.LG)

paper · pdf · doi:10.48550/arxiv.2410.19835

openalex publication_date 2024/10/19 · openalex created_date 2024/11/14 · openalex updated_date 2026/07/28

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.

Cited by

• Towards Structured Knowledge: Advancing Triple Extraction from Regional Trade Agreements using Large Language Models

Related

• Accurate prediction of international trade flows: Leveraging knowledge graphs and their embeddings
• The Knowledge Graph for Macroeconomic Analysis with Alternative Big Data
• International Trade Network: Statistical Analysis and Modeling
• Machine learning and economic forecasting: the role of international trade networks
• Mapping Global Value Chains at the Product Level