Getting Ahead of Armed Conflict

Aid groups were caught off-guard by the violence that began in Syria in 2011 partly because prediction models had estimated a mere 0.05% chance of violence there.

But predictions are improving thanks to better data, machine learning, and combining the strengths of different models.

Take Ethiopia—where violence has ensued since the election of Abiy Ahmed, now a controversial Nobel Peace Prize winner.

Uppsala University’s newer ViEWS model predicted violence there based on 3 types of conflict risk. 

The improved models are more likely to offer crucial warning signs for humanitarian groups looking to efficiently direct aid.

MIT Technology Review

Comments +

0 comments

Post a Comment

Restricted HTML

  • Lines and paragraphs break automatically.
  • Web page addresses and email addresses turn into links automatically.
CAPTCHA
This question is for testing whether or not you are a human visitor and to prevent automated spam submissions.
Back to top