Working women and caste in India: A study of social disadvantage using feature attribution

Women belonging to the socially disadvantaged caste-groups in India have historically been engaged in labour-intensive, blue-collar work. We study whether there has been any change in the ability to predict a woman’s work-status and work-type based on her caste by interpreting machine learning model...

Descripción completa

Detalles Bibliográficos
Autores principales: Joshi, Kuhu, Joshi, Chaitanya K.
Formato: Conference Paper
Lenguaje:Inglés
Publicado: 2019
Materias:
Acceso en línea:https://hdl.handle.net/10568/146126
_version_ 1855521730421850112
author Joshi, Kuhu
Joshi, Chaitanya K.
author_browse Joshi, Chaitanya K.
Joshi, Kuhu
author_facet Joshi, Kuhu
Joshi, Chaitanya K.
author_sort Joshi, Kuhu
collection Repository of Agricultural Research Outputs (CGSpace)
description Women belonging to the socially disadvantaged caste-groups in India have historically been engaged in labour-intensive, blue-collar work. We study whether there has been any change in the ability to predict a woman’s work-status and work-type based on her caste by interpreting machine learning models using feature attribution. We find that caste is now a less important determinant of work for the younger generation of women compared to the older generation. Moreover, younger women from disadvantaged castes are now more likely to be working in white-collar jobs.
format Conference Paper
id CGSpace146126
institution CGIAR Consortium
language Inglés
publishDate 2019
publishDateRange 2019
publishDateSort 2019
record_format dspace
spelling CGSpace1461262024-10-25T07:55:23Z Working women and caste in India: A study of social disadvantage using feature attribution Joshi, Kuhu Joshi, Chaitanya K. innovation gender machine learning capacity development labour workforce women caste systems female labour Women belonging to the socially disadvantaged caste-groups in India have historically been engaged in labour-intensive, blue-collar work. We study whether there has been any change in the ability to predict a woman’s work-status and work-type based on her caste by interpreting machine learning models using feature attribution. We find that caste is now a less important determinant of work for the younger generation of women compared to the older generation. Moreover, younger women from disadvantaged castes are now more likely to be working in white-collar jobs. 2019-05-21 2024-06-21T09:05:54Z 2024-06-21T09:05:54Z Conference Paper https://hdl.handle.net/10568/146126 en Open Access Joshi, Kuhu; and Joshi, Chaitanya K. 2019. Working women and caste in India: A study of social disadvantage using feature attribution. Presented at the AI for Social Good ICLR2019 Workshop, in Ernest N. Morial Convention Center, New Orleans, United States, May 06, 2019. https://aiforsocialgood.github.io/iclr2019/accepted/track1/pdfs/18_aisg_iclr2019.pdf
spellingShingle innovation
gender
machine learning
capacity development
labour
workforce
women
caste systems
female labour
Joshi, Kuhu
Joshi, Chaitanya K.
Working women and caste in India: A study of social disadvantage using feature attribution
title Working women and caste in India: A study of social disadvantage using feature attribution
title_full Working women and caste in India: A study of social disadvantage using feature attribution
title_fullStr Working women and caste in India: A study of social disadvantage using feature attribution
title_full_unstemmed Working women and caste in India: A study of social disadvantage using feature attribution
title_short Working women and caste in India: A study of social disadvantage using feature attribution
title_sort working women and caste in india a study of social disadvantage using feature attribution
topic innovation
gender
machine learning
capacity development
labour
workforce
women
caste systems
female labour
url https://hdl.handle.net/10568/146126
work_keys_str_mv AT joshikuhu workingwomenandcasteinindiaastudyofsocialdisadvantageusingfeatureattribution
AT joshichaitanyak workingwomenandcasteinindiaastudyofsocialdisadvantageusingfeatureattribution