The ACLED Conflict Alert System (CAST) is a tool for forecasting political violence globally. It uses machine learning to predict political violence events in every country in the world at the national and subnational level up to six months into the future. This tool is unique in its comprehensive use of ACLED data; its global, national, and subnational reach; its prediction of a broad range of violent events; and its emphasis on the occurrence of these events and their escalation, rather than only on conflict onset.
In addition, this tool allows users to view forecasted events in a specific area and utilizes Explanatory AI to disentangle the factors driving each forecast to see how they compare to past trends. CAST has the power to support policymakers by providing high-quality forecasts that can be used for priority setting, resource allocation, and forward-looking strategic planning.
The Armed Conflict Location & Event Data Project (ACLED) is a disaggregated data collection, analysis, and crisis mapping project. ACLED is the highest quality and most widely used real-time data and analysis source on political violence and protest around the world. Practitioners, researchers, journalists, and governments depend on ACLED for the latest reliable information on current conflict and disorder patterns.
CAST has been accessed by +1000 government and civil society users over 2700 times since March 2023, who apply it to strategic planning in different crisis settings around the world.