Artificial Neural Network Model to Predict the Exportation of Traditional Products of Colombia DOI Creative Commons

Andrea C. Gómez,

Lilian A. Bejarano, Helbert Espitia

et al.

Computation, Journal Year: 2024, Volume and Issue: 12(11), P. 221 - 221

Published: Nov. 4, 2024

This article develops the design, training, and validation of a computational model to predict exportation traditional Colombian products using artificial neural networks. work aims obtain single multilayer network. The number historical input data (delays), layers, neurons were considered for network design. In this way, an experimental design 64 configurations was performed. main arduousness addressed in is significant difference (in tons) values products. results show effect that occurs due different range values, one proposals made allows limitation be handled appropriately. summary, seeks provide essential information formulating efficient practical application.

Language: Английский

Exploring novelties in the causal relationship between economic complexity and natural resource rent: Empirical insights from Nigeria and South Africa DOI Creative Commons

Olaniyi Clement Olalekan,

Odhiambo Nicholas Mbaya

Journal of Open Innovation Technology Market and Complexity, Journal Year: 2025, Volume and Issue: unknown, P. 100483 - 100483

Published: Jan. 1, 2025

Language: Английский

Citations

2
Harnessing Graph Neural Networks to Predict International Trade Flows DOI Creative Commons
Bassem Sellami, Chahinez Ounoughi, Tarmo Kalvet

et al.

Big Data and Cognitive Computing, Journal Year: 2024, Volume and Issue: 8(6), P. 65 - 65

Published: June 7, 2024

In the realm of international trade and economic development, prediction flows between countries is crucial for identifying export opportunities. Commonly used log-linear regression models are constrained due to difficulties when dealing with extensive, high-cardinality datasets, utilization machine learning techniques in predictions offers new possibilities. We examine predictive power Graph Neural Networks (GNNs) estimating value bilateral countries. work detailed UN Comtrade data that represent annual goods any two world more than 5000 product groups. explore different types GNNs, namely Convolutional (GCNs) Attention (GATs), by applying them flow data. This study evaluates effectiveness GNNs relative traditional such as random forest examines possible effects drift on their performance. Our findings reveal superior capability suggesting modeling complex relationships. The research presented this a data-driven foundation decision-making relevant business strategies policymaking it helps markets, products, sectors significant development potential.

Language: Английский

Citations

4
Gravity Models Meets Random Forests: Explaining the impact of geopolitical tensions on trade flows DOI

Costanza Bosone,

Paolo Giudici

Published: Jan. 1, 2025

Language: Английский

Citations

0
High-accuracy prediction of international raw material trade flows using temporal fusion transformer DOI

Djihad Arrar,

Chahinez Ounoughi, Nadjet Kamel

et al.

International Journal of Data Science and Analytics, Journal Year: 2025, Volume and Issue: unknown

Published: May 15, 2025

Language: Английский

Citations

0
Artificial Neural Network Model to Predict the Exportation of Traditional Products of Colombia DOI Creative Commons

Andrea C. Gómez,

Lilian A. Bejarano, Helbert Espitia

et al.

Computation, Journal Year: 2024, Volume and Issue: 12(11), P. 221 - 221

Published: Nov. 4, 2024

This article develops the design, training, and validation of a computational model to predict exportation traditional Colombian products using artificial neural networks. work aims obtain single multilayer network. The number historical input data (delays), layers, neurons were considered for network design. In this way, an experimental design 64 configurations was performed. main arduousness addressed in is significant difference (in tons) values products. results show effect that occurs due different range values, one proposals made allows limitation be handled appropriately. summary, seeks provide essential information formulating efficient practical application.

Language: Английский

Citations

0