In an effort to provide early warning capabilities, the U.S. Department of Defense’s Integrated Crisis Early Warning System (ICEWS) and IARPA’s Open Source Indicators (OSI) programs want to leverage novel statistical and machine learning techniques using publicly available data sources to forecast societal such as civil unrest and disease outbreaks with a high degree of accuracy.
Participants are encouraged to develop and test innovative forecasting methods that ingest and process publicly available data sources to predict Military Activity, Non-violent Civil Unrest, and Infectious Disease in specific places of interest.
Participant forecasts will be scored across a three-month rolling window. Every month, IAPRA will score those participants who have sent forecasts for three consecutive months. Scoring will be based on four metrics including forecast lead time, location accuracy, date accuracy, and facet actor/event-type matching. This challenge is scheduled to run from July 2018 until early 2019 when winners are announced.
Technologists, data scientists, and machine learning engineers who are skilled at breaking down complex data are encouraged to join. Individuals ranging from private industry and academia are all eligible to participate and win prizes. The Mercury Challenge Team believes success in this challenge can prove to be a strong addition to any data science practitioner’s portfolio.
The Mercury Challenge seeks innovative solutions and methods for the automated generation of event forecasts in the Middle East and North Africa.
The three specific event classes of interest are:
- Military Activity (MA) in Egypt, Saudi Arabia, Iraq, Syria, Qatar, Lebanon, Jordan, and Bahrain:
- Conflict – Incident where police, military, or other state/government security forces take action in some way; and
- Force posture – A newsworthy action of police, military, or other state/government security forces that does not involve the use of deadly force.
- Non-violent Civil Unrest (CU) in Egypt and Jordan, such as demonstrations, marches and protests:
- Daily count of non-violent civil unrest events in Egypt
- Weekly count of non-violent civil unrest events in Jordan
- Weekly count of non-violent civil unrest events in a 75km radius of Tahrir Square, Egypt
- Monthly count of non-violent civil unrest events in the Jordanian provinces of Amman, Madaba, and Irbid.
- Infectious disease in Saudi Arabia: Weekly MERS count.
Participants with the best winning solutions will be eligible to win from a prize pool of $100,000, which will be distributed across a series of very difficult country/event combination.
For example: “Predict Non-violent Civil Unrest events in Egypt, but far away from Cairo, during the month of August 2018″
Challenge participants can win prizes for having top scores across thirteen separate categories. The top scorers after each scoring period will earn the Top Prize for that given period. Regular and early participation will provide more chances of winning!
Read the full Prize Calculation Documentation for all the details on prizes.