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.

In most developing countries a shortage of long-term, local-currency financing for small-scale infrastructure projects impedes local economic development. Inadequate fiscal transfers, little own source revenue and low creditworthiness make it difficult for local governments to fully fund projects on their own. This paper proposes the use of project finance as a means to attract financing from domestic banks and institutional investors. Donors can play a catalytic role by providing technical assistance to develop projects and credit enhancement to attract commercial financing.