AI for Social Risk Forecasting and Explanation: The Power of Machine Learning–Based Social Risk Models

Christopher Brian Mahony, Varalakshmi Vemuru, Aly Rahim and Daniel P. Owen

No 209567, The Social Policy and Labor Discussion Paper Series from The World Bank

Abstract: AI- and machine learning–based social risk forecasting and explanation are applied across fragile and climate-affected contexts to predict change in conflict (DRC), population movement (Horn of Africa), and crime (a SIDS), using large multimodal datasets (satellite imagery, NLP on news/social media, economic and climate indicators, geospatial data). Three proof-of-concept models achieve out-of-sample accuracies of 63–76% (conflict) and 70–74% (population change), and generate crime risk proxies where official statistics are scarce. Key associated factors include language about sensitive topics and political actors, economic pressures and prices, climate stress, and social perceptions. Results illustrate how social science–informed AI complements conventional analytics and supports policy and operations for risk monitoring, early action, and targeted resource allocation

Date: 2026-04-01
References: Add references at CitEc
Citations:

Downloads: (external link)
https://documents.worldbank.org/curated/en/0993594 ... 894-f11de93018f2.pdf (application/pdf)
Our link check indicates that this URL is bad, the error code is: 404 Not Found (https://documents.worldbank.org/curated/en/099359404132636690/pdf/IDU-81301edf-6a95-4ec8-b894-f11de93018f2.pdf [302 Found]--> http://documents1.worldbank.org/curated/en/099359404132636690/pdf/IDU-81301edf-6a95-4ec8-b894-f11de93018f2.pdf [301 Moved Permanently]--> https://documents1.worldbank.org/curated/en/099359404132636690/pdf/IDU-81301edf-6a95-4ec8-b894-f11de93018f2.pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:wbk:hdnspu:209567

Access Statistics for this paper

More papers in The Social Policy and Labor Discussion Paper Series from The World Bank 1818 H Street, N.W., Washington, DC 20433. Contact information at EDIRC.
Bibliographic data for series maintained by Aaron F Buchsbaum ().