World Bank (2025) Working paper / technical note

AI-Powered Refugee Forecasting

World Bank

Ref: SRC-004-UGA-001

https://thedocs.worldbank.org/en/doc/4d816aaea9713abd30f63c6b92e1e79b-0090082025/original/AI-Powered-refugee-forecasting.pdf

Accessed: 3/24/2026

Summary

One-page brief confirming the model ingests 90+ variables across economic, conflict, perception, and climate data to predict displacement scale, location, and timing. Funded by World Bank Multi-Donor Trust Fund for Forced Displacement and PROSPECTS Partnership with Kingdom of the Netherlands.

View Harvard reference

World Bank (2025). 'AI-Powered Refugee Forecasting' [one-pager]. Washington, DC: World Bank. Available at: https://thedocs.worldbank.org/en/doc/4d816aaea9713abd30f63c6b92e1e79b-0090082025/original/AI-Powered-refugee-forecasting.pdf (Accessed 24 March 2026).

Attached File

PDF

SRC-004-UGA-001_AI-Powered_Refugee_Forecasting.pdf 146 KB

Download

Linked Cases (1)

UGA-001 UGA Operational Deployment (Limited Rollout)

AI-Enabled Refugee Forecasting for Uganda's Displacement Crisis Response Mechanism (DCRM)

Social assistance Classical ML