Gaskin, T., Demirel, G., Wolfram, MT. et al. Modelling global trade with optimal transport. Nat Commun
Objective:
- Employ optimal transport and a deep neural network to learn a time-dependent cost function from data
Case:
- Global countries
Methodology:
- Entropy-regularized optimal transport
- Neural inverse optimal transport
- Neural network
Data Source
- FAO trade matrix
Findings:
- Low-income countries experienced disproportionately higher increase in trade costs due to war in Ukraine’s impact on wheat markets
