Tracking Internally Displaced Persons Using AI

Crisis context/scope of workInternal displacement globally  
Geographical scopeGlobal
Project periodNovember 2019 – December 2020
Donors/partnersInternal Displacement Monitoring Centre (IDMC)
BudgetUSD 327,000
Technologies used: Django, Postgres, PostGIS, React, Mapbox, D3.js
ProblemDFS’ solution
More than 50 million people throughout the world are internally displaced. UNHCR has called internally displaced people “among the most vulnerable in the world.” 
Thousands of internal displacement crises are tracked and analyzed by IDMC, one of the world’s most definitive sources of internal displacement data. 
IDMC previously relied on a small IT team to collect and securely store reliable, timely, and longitudinal data on millions of displaced people from over 188 countries, but the vast amount of collected data created challenges for the team. Their limited capacity slowed the international community’s ability to respond to, and ultimately reduce, the effects of internal displacements across all continents.
IDMC partnered with DFS to introduce multiple data management tools, aided by AI to better process, store, and analyze internal displacement trends enabling faster, more robust humanitarian responses from the field.  The partnership replaced IDMC’s manual processes with IDETECT, a tool that analyzes thousands of global news sources each day by utilizing natural language processing.  DFS redeveloped IDMC web applications to collect, analyze, and report internal displacement data more efficiently. The resulting smart reporting had a significant role in reporting on internal displacement during the COVID-19 pandemic.   Read more