Accurate prediction of international trade flows: Leveraging knowledge graphs and their embeddings

被引:6
作者
Rincon-Yanez, Diego [1 ]
Ounoughi, Chahinez [2 ]
Sellami, Bassem [2 ,3 ]
Kalvet, Tarmo [4 ]
Tiits, Marek [4 ]
Senatore, Sabrina [1 ]
Ben Yahia, Sadok [2 ]
机构
[1] Univ Salerno, Dept Informat & Elect Engn & Appl Math, Via Giovanni Paolo II 132, I-84084 Fisciano, Italy
[2] Tallinn Univ Technol, Dept Software Sci, Akad Tee 15a, EE-12618 Tallinn, Estonia
[3] Univ Tunis El Manar, Fac Sci Tunis, Lab Micol Pathol & Biomarkers, Tunis 1092, Tunisia
[4] Tallinn Univ Technol, Dept Business Adm, Ehitajate Tee 5, EE-12616 Tallinn, Estonia
基金
欧盟地平线“2020”;
关键词
Knowledge Graph; Knowledge Graph Embeddings; Gravity model; International Trade;
D O I
10.1016/j.jksuci.2023.101789
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Knowledge representation (KR) is vital in designing symbolic notations to represent real-world facts and facilitate automated decision-making tasks. Knowledge graphs (KGs) have emerged so far as a popular form of KR, offering a contextual and human-like representation of knowledge. In international economics, KGs have proven valuable in capturing complex interactions between commodities, companies, and countries. By putting the gravity model, which is a common economic framework, into the process of building KGs, important factors that affect trade relationships can be taken into account, making it possible to predict international trade patterns. This paper proposes an approach that leverages Knowledge Graph embeddings for modeling international trade, focusing on link prediction using embeddings. Thus, valuable insights are offered to policymakers, businesses, and economists, enabling them to anticipate the effects of changes in the international trade system. Moreover, the integration of traditional machine learning methods with KG embeddings, such as decision trees and graph neural networks are also explored. The research findings demonstrate the potential for improving prediction accuracy and provide insights into embedding explainability in knowledge representation. The paper also presents a comprehensive analysis of the influence of embedding methods on other intelligent algorithms.
引用
收藏
页数:11
相关论文
共 57 条
[1]  
[Anonymous], 2023, Comtrade
[2]  
[Anonymous], 2020, Trading for Development in the Age of Global Value Chains, DOI DOI 10.1596/978-1-4648-1457-0
[3]  
[Anonymous], 2022, The CEPII gravity database. 202211 version
[4]   Comparing International Market Selection Methods Using Export Potential Values for South Africa [J].
Aucamp, Mariska ;
Steenkamp, Ermie Annelies ;
Bezuidenhout, Carli .
INTERNATIONAL TRADE JOURNAL, 2025, 39 (01) :55-77
[5]  
Bergeijk P., 2010, The Gravity Model in International Trade: Advances And Applications
[6]  
Besold T.R., 2017, Neuro-Symbolic Artificial Intelligence: The State of the Art
[7]  
Bordes A., 2013, P 26 INT C NEURAL IN, P2787
[8]   Combining Machine Learning and Semantic Web: A Systematic Mapping Study [J].
Breit, Anna ;
Waltersdorfer, Laura ;
Ekaputra, Fajar J. ;
Sabou, Marta ;
Ekelhart, Andreas ;
Iana, Andreea ;
Paulheim, Heiko ;
Portisch, Jan ;
Revenko, Artem ;
Ten Teije, Annette ;
Van Harmelen, Frank .
ACM COMPUTING SURVEYS, 2023, 55 (14S)
[9]  
Cattaneo O, 2010, GLOBAL VALUE CHAINS IN A POSTCRISIS WORLD: A DEVELOPMENT PERSPECTIVE, P3
[10]  
CEPII-BACI, 2023, D7.5-Replicability at International Level-Application to Canada