Humanitarian decision-makers have called for the increased use of predictive analytics to inform anticipatory action. However, translating the outputs of predictive models into timely and appropriate responses remains a challenge for several reasons:
- First, there is no common standard for documenting predictive models and their intended use which highlights the critical aspects for the application of models in the humanitarian sector.
- Second, there is no common standard or mechanism for assessing the technical rigor and operational readiness of predictive models in the sector.
- Third, the development of predictive models is often led by technical specialists who may not consider important ethical concerns that the application of models in humanitarian contexts may entail.
The Centre for Humanitarian Data (‘the Centre’) has been working with our partners to understand the current state of model development and use in humanitarian operations. We have noted a clear desire for quality assurance of models by partners, with the Centre identified as having a unique role to facilitate a peer review process.
The following Peer Review Framework for Predictive Analytics in Humanitarian Response aims to create standards and processes for the use of models in our sector. It is based on research with experts and stakeholders across a range of organizations that design and use predictive models. The Framework also draws on best practices from academia and the private sector.
Quality assurance is one of three areas of focus for the Centre’s predictive analytics workstream. We also work on developing new models and supporting existing partner models for use in humanitarian operations, and on community and capacity building. Learn more about our work on predictive analytics on the Centre’s website: https://centre.humdata.org.
- UN Office for the Coordination of Humanitarian Affairs
- To learn more about OCHA's activities, please visit https://www.unocha.org/.