Leveraging unsupervised machine learning to examine women's vulnerability to climate change

We provide an application of machine learning to identify the distributional consequences of climate change in Malawi. We compare climate impact estimates based on drought indicators established objectively from the k-means algorithm to more traditional measures. Young women affected by drought were...

Full description

Bibliographic Details
Main Authors: Caruso, German, Mueller, Valerie, Villacis, Alexis
Format: Journal Article
Language:Inglés
Published: Wiley 2024
Subjects:
Online Access:https://hdl.handle.net/10568/145032
_version_ 1855515672869601280
author Caruso, German
Mueller, Valerie
Villacis, Alexis
author_browse Caruso, German
Mueller, Valerie
Villacis, Alexis
author_facet Caruso, German
Mueller, Valerie
Villacis, Alexis
author_sort Caruso, German
collection Repository of Agricultural Research Outputs (CGSpace)
description We provide an application of machine learning to identify the distributional consequences of climate change in Malawi. We compare climate impact estimates based on drought indicators established objectively from the k-means algorithm to more traditional measures. Young women affected by drought were 5 percentage points more likely to be married by 18 than those living in nondrought areas. Our approach generates robust results when varying the number of clusters and definition of treatment status. In some cases, we find the design using k-means to define treatment is more likely to satisfy the assumptions underlying the difference-in-differences strategy than when using arbitrary thresholds. Projections from the estimates indicate future drought risk may lead to larger declines in labor productivity due to women's engagement in early age marriage than other factors affecting their participation rates. Under the extreme representative concentration pathway scenario, drought exposure encourages the exit of 3.3 million women workers by 2100.
format Journal Article
id CGSpace145032
institution CGIAR Consortium
language Inglés
publishDate 2024
publishDateRange 2024
publishDateSort 2024
publisher Wiley
publisherStr Wiley
record_format dspace
spelling CGSpace1450322025-04-08T18:36:18Z Leveraging unsupervised machine learning to examine women's vulnerability to climate change Caruso, German Mueller, Valerie Villacis, Alexis machine learning women vulnerability climate change We provide an application of machine learning to identify the distributional consequences of climate change in Malawi. We compare climate impact estimates based on drought indicators established objectively from the k-means algorithm to more traditional measures. Young women affected by drought were 5 percentage points more likely to be married by 18 than those living in nondrought areas. Our approach generates robust results when varying the number of clusters and definition of treatment status. In some cases, we find the design using k-means to define treatment is more likely to satisfy the assumptions underlying the difference-in-differences strategy than when using arbitrary thresholds. Projections from the estimates indicate future drought risk may lead to larger declines in labor productivity due to women's engagement in early age marriage than other factors affecting their participation rates. Under the extreme representative concentration pathway scenario, drought exposure encourages the exit of 3.3 million women workers by 2100. 2024-12 2024-06-06T17:34:59Z 2024-06-06T17:34:59Z Journal Article https://hdl.handle.net/10568/145032 en Limited Access Wiley Caruso, German; Mueller, Valerie; and Villacis, Alexis. 2024. Leveraging unsupervised machine learning to examine women's vulnerability to climate change. Applied Economic Perspectives and Policy 46(4): 1355-1378. https://doi.org/10.1002/aepp.13444
spellingShingle machine learning
women
vulnerability
climate change
Caruso, German
Mueller, Valerie
Villacis, Alexis
Leveraging unsupervised machine learning to examine women's vulnerability to climate change
title Leveraging unsupervised machine learning to examine women's vulnerability to climate change
title_full Leveraging unsupervised machine learning to examine women's vulnerability to climate change
title_fullStr Leveraging unsupervised machine learning to examine women's vulnerability to climate change
title_full_unstemmed Leveraging unsupervised machine learning to examine women's vulnerability to climate change
title_short Leveraging unsupervised machine learning to examine women's vulnerability to climate change
title_sort leveraging unsupervised machine learning to examine women s vulnerability to climate change
topic machine learning
women
vulnerability
climate change
url https://hdl.handle.net/10568/145032
work_keys_str_mv AT carusogerman leveragingunsupervisedmachinelearningtoexaminewomensvulnerabilitytoclimatechange
AT muellervalerie leveragingunsupervisedmachinelearningtoexaminewomensvulnerabilitytoclimatechange
AT villacisalexis leveragingunsupervisedmachinelearningtoexaminewomensvulnerabilitytoclimatechange