Working Papers

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.

As developing countries pursue infrastructure projects, they should aim to address a combination of the pandemic, climate, inequality, and other crises with the right mix of economic and social infrastructure. To do this, governments must invest in a national infrastructure planning process, align planning with the SDGs, and prioritize sustainable infrastructure over infrastructure that does not put people and the planet first. There is no silver bullet for all the challenges; however, incremental changes based on innovative precedents can potentially make a difference on the ground. This paper proposes an analytical framework to consider these challenges and concludes with possible…