Skip to content

Commit

Permalink
Create README.md
Browse files Browse the repository at this point in the history
  • Loading branch information
aywaldron authored Nov 3, 2019
1 parent f8fb74f commit 624db35
Showing 1 changed file with 21 additions and 0 deletions.
21 changes: 21 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,21 @@
# trade-communities
Predicting international trade communities from world development indicators

## The problem

This project aimed to determine the predictive power of world
development indicators for international trade communities, while inspecting changes and trends in
these communities over time. It was hypothesized that world development indicators may contain the
right balance of both sociologically and economically-driven information to predict international trade
communities.

In order to test this hypothesis, a weighted, directed network was created using export FOB data
from the International Monetary Fund’s (IMF) Direction of Trade (DOT) statistics. Communities were
found in this network using the modularity maximization algorithm explained in [1]. These community
classifications were then predicted from the World Bank’s World Development Indicators using a
random forest classifier.

## References

1. Leicht EA, Newman ME. “Community structure in directed networks”. Phys Rev Lett. 2008
Mar 21; 100(11):118703. Epub 2008 Mar 21.

0 comments on commit 624db35

Please sign in to comment.