Research and resources

Poverty prediction and targeting with digital data

Cider was developed from a line of research on estimating poverty from machine learning and mobile phone data that dates back to 2015. The following papers provide context on this research and discussions of the accuracy, fairness, and practicality of phone-based targeting in several contexts.

• Aiken, E. et al. (2021). Machine learning and mobile phone data can improve the targeting of humanitarian assistance. Nature 603 pages 864-870.

• Aiken, E. et al. (2020). Targeting development aid with machine learning and mobile phone data: Evidence from an anti-poverty intervention in Afghanistan. ACM SIGCAS Conference on Computing and Sustainable Societies.

• Blumenstock, J. (2018). Estimating economic characteristics with phone data. American Economic Review: Papers and Proceedings.

• Blumenstock, J., Cadamuro, G., and On, R. (2015). Predicting poverty and wealth from mobile phone metadata. Science 350.

AI ethics for the humanitarian and development fields

• DSEG - Data Science and Ethics Group (2020). A Framework For the Ethical Use of Advanced Data Science Methods in the Humanitarian Sector.

• Leslie, D. (2019). Understanding artificial intelligence ethics and safety: A guide for the responsible design and implementation of AI systems in the public sector. The Alan Turing Institute.

• High-level Expert Group on Artificial Intelligence set up by the European Commision (2019). Ethics Guidelines for Trustworthy AI.

• The International Development Innovation Alliance (IDIA) Working Group on Artificial Intelligence & Development. Artificial Intelligence in International Development: A Discussion Paper.

• fAIr LAC: Latin America and the Caribbean Alliance for Ethical and Responsible Use of AI.