Loading...
Interpreting wealth distribution via poverty map inference using multimodal data
Title / Series / Name
Publication Volume
Publication Issue
Pages
Authors
EspÃn-Noboa, Lisette
Kertész, János
Karsai, Márton
Kertész, János
Karsai, Márton
Editors
Keywords
deep learning
high-resolution spatial inference
machine learning
online crowd-sourced data
poverty maps
satellite images
Computer Networks and Communications
Software
high-resolution spatial inference
machine learning
online crowd-sourced data
poverty maps
satellite images
Computer Networks and Communications
Software
URI
https://hdl.handle.net/20.500.14018/26514
Abstract
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.
Topic
Publisher
Place of Publication
Type
Conference paper
Date
2023-04-30
Language
ISBN
9781450394161
9781450394161
9781450394161
Identifiers
10.1145/3543507.3583862