# Combined models of violent conflict and natural hazards improve predictions of household mobility in Bangladesh

## TL;DR

The paper shows that combining models of conflict and natural hazards improves predictions of household mobility in Bangladesh, with remittance-receiving households more likely to move.

## Contribution

The novel contribution is integrating conflict and natural hazard data with household characteristics to improve mobility predictions using machine learning.

## Key findings

- Combining conflict and hazard data improves predictions of household mobility.
- Households with remittances are more likely to move, while those with loans tend to stay.
- Interactions between violence and natural hazards amplify mobility.

## Abstract

In 2023, the United Nations High Commissioner for Refugees reported over 110 million displaced individuals globally, many in regions facing extreme weather and violence. Here we examine how these crises interact to shape household mobility in Bangladesh. Using data linking local conflict events, natural hazards, and household characteristics from 2011 to 2018, we apply machine learning models to capture complex, non-linear relationships between these risks. We find that combining conflict and hazard information improves predictions of household mobility. While exposure to violence or disasters increases mobility, households with remittances are more likely to move, whereas those with loans often remain. Interactions, such as between one-sided violence and landslides, further amplify movement, highlighting the importance of understanding how multiple stressors jointly influence household decisions.

In Bangladesh, exposure to violence or natural disasters increases mobility, and households with remittances are more likely to move, according to machine-learning analysis.