# Interpreting wealth distribution via poverty map inference using multimodal data

arXiv: https://arxiv.org/abs/2302.10793 · HTML: https://mlsanity.com/paper/2302.10793/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 76 references that are in the map.
- First posted on arXiv 17 Feb 2023.

## Builds on (most cited first, 13 of 13)

- [Class-Balanced Loss Based on Effective Number of Samples](https://mlsanity.com/paper/1901.05555/) (2019)
- [Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions](https://mlsanity.com/paper/2107.13782/) (2021)
- [Generating Interpretable Poverty Maps using Object Detection in Satellite Images](https://mlsanity.com/paper/2002.01612/) (2020)
- [Survey: Image Mixing and Deleting for Data Augmentation](https://mlsanity.com/paper/2106.07085/) (2021)
- [Micro-Estimates of Wealth for all Low- and Middle-Income Countries](https://mlsanity.com/paper/2104.07761/) (2021)
- [Mapping the world population one building at a time](https://mlsanity.com/paper/1712.05839/) (2017)
- [Predicting Twitter User Socioeconomic Attributes with Network and Language Information](https://mlsanity.com/paper/1804.04095/) (2018)
- [High-Resolution Poverty Maps in Sub-Saharan Africa](https://mlsanity.com/paper/2009.00544/) (2020)
- [Social media fingerprints of unemployment](https://mlsanity.com/paper/1411.3140/) (2014)
- [Location, Occupation, and Semantics based Socioeconomic Status Inference on Twitter](https://mlsanity.com/paper/1901.05389/) (2019)
- [Mapping urban socioeconomic inequalities in developing countries through Facebook advertising data](https://mlsanity.com/paper/2105.13774/) (2021)
- [Socioeconomic correlations and stratification in social-communication networks](https://mlsanity.com/paper/1612.04580/) (2016)
- [Correlations and dynamics of consumption patterns in social-economic networks](https://mlsanity.com/paper/1801.08856/) (2018)

## Built on by (most cited first, 1 of 1)

- [A Comparative Analysis of Wealth Index Predictions in Africa between three Multi-Source Inference Models](https://mlsanity.com/paper/2408.01631/) (2024)

## Abstract (arXiv)

Poverty maps are essential tools for governments and NGOs to track socioeconomic changes and adequately allocate infrastructure and services in places in need. Sensor and online crowd-sourced data combined with machine learning methods have provided a recent breakthrough in poverty map inference. However, these methods do not capture local wealth fluctuations, and are not optimized to produce accountable results that guarantee accurate predictions to all sub-populations. Here, we propose a pipeline of machine learning models to infer the mean and standard deviation of wealth across multiple geographically clustered populated places, and illustrate their performance in Sierra Leone and Uganda. These models leverage seven independent and freely available feature sources based on satellite images, and metadata collected via online crowd-sourcing and social media. Our models show that combined metadata features are the best predictors of wealth in rural areas, outperforming image-based models, which are the best for predicting the highest wealth quintiles. Our results recover the local mean and variation of wealth, and correctly capture the positive yet non-monotonous correlation between them. We further demonstrate the capabilities and limitations of model transfer across countries and the effects of data recency and other biases. Our methodology provides open tools to build towards more transparent and interpretable models to help governments and NGOs to make informed decisions based on data availability, urbanization level, and poverty thresholds.