Economic Complexity
For decades, economics has relied on the use of statistics as its battle-horse for empirical analysis. Today, machine learning tools, from recommender systems to dimensionality reduction techniques, provide a new way to understand economic development.
During the last decade, the field of economic complexity emerged as an important quantitative tool for the understanding of economic geography, development, and innovation. Indicators, such as the Economic Complexity Index (ECI), have become popular statistics of the economic capacities of locations, and concepts such as relatedness, have helped improve our understanding of the diversification paths undertaken by national and regional economies.
The Center for Collective Learning works on the development and application of machine learning techniques applied to economic development. Building on our vast experience on the fields of economic complexity, economic development, and economic geography, we provide a new predictive lens to understand the evolution of economies, from cities to nations.
The Observatory of Economic Complexity (OEC) (2011) makes more than fifty years of international trade data available through dozens of millions of interactive visualizations. It is the world’s most popular site to visualize international trade data.
The OEC was developed by Alexander Simoes as part of his requirement to complete his Masters in Media, Arts, and Sciences.
DataViva (2013) made available data for the entire economy of Brazil, including exports and imports for each municipality and product, and occupation data for every municipality, industry, and occupation.
DataViva was created in a collaboration between FapeMIG, DataWheel, and the Macro Connections group at the MIT Media Lab.
