Menu

Working Papers

Displaying 1 - 2 of 2
Economic Analysis and Policy

This paper proposes the use of synthetic training data generated by large language models
to improve machine learning SDG classifiers. It shows that supplementing existing training data with
synthetic data produced by the ChatGPT tool improves the performance of the SDGClassy classifier.
This addition of synthetic data is especially useful in building SDG classifiers given the limited availability
of properly labeled data and the complex, interconnected nature of the SDGs. Synthetic data thus enables
more effective machine-learning applications in this context.

Sustainable Development

This paper examines the relationship between “Transformative Change,” advocated by the 2030 Agenda for sustainable development, and “Structural Change,” which has been a longstanding and important concept in Development Economics. It shows that while structural change is still relevant, growing concerns for social development and environmental protection made it necessary to switch to the more encompassing concept of “Transformative Change” that provides greater space for inclusion and interaction of all three dimensions of sustainable development. The paper notes that, in the era of greater globalization, countries have followed more varied patterns of structural change, all of which…