An Explainable Forecasting System for Humanitarian Needs Assessment

Rahul Nair, Bo Schwartz Madsen, Alexander Kjærum

AAAI 2023 pp. 15569-15575

doi:10.1609/AAAI.V37I13.26846 /aaai/2023/nair2023aaai-explainable/

Abstract

We present a machine learning system for forecasting forced displacement populations deployed at the Danish Refugee Council (DRC). The system, named Foresight, supports long term forecasts aimed at humanitarian response planning. It is explainable, providing evidence and context supporting the forecast. Additionally, it supports scenarios, whereby analysts are able to generate forecasts under alternative conditions. The system has been in deployment since early 2020 and powers several downstream business functions within DRC. It is central to our annual Global Displacement Report which informs our response planning. We describe the system, key outcomes, lessons learnt, along with technical limitations and challenges in deploying machine learning systems in the humanitarian sector.

PDF AAAI Semantic Scholar

Cite

Text

Nair et al. "An Explainable Forecasting System for Humanitarian Needs Assessment." AAAI Conference on Artificial Intelligence, 2023. doi:10.1609/AAAI.V37I13.26846

Markdown

[Nair et al. "An Explainable Forecasting System for Humanitarian Needs Assessment." AAAI Conference on Artificial Intelligence, 2023.](https://mlanthology.org/aaai/2023/nair2023aaai-explainable/) doi:10.1609/AAAI.V37I13.26846

BibTeX

@inproceedings{nair2023aaai-explainable,
  title     = {{An Explainable Forecasting System for Humanitarian Needs Assessment}},
  author    = {Nair, Rahul and Madsen, Bo Schwartz and Kjærum, Alexander},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2023},
  pages     = {15569-15575},
  doi       = {10.1609/AAAI.V37I13.26846},
  url       = {https://mlanthology.org/aaai/2023/nair2023aaai-explainable/}
}