Despite their growing participation in the labor market, women who decide to go out and look for a job face greater difficulties in obtaining it. The participation of women in the labor force is considerably lower, even if entering the labor market the possibility of actually finding a job is also less than the chance that men have of doing so (CIPPEC, 2019). Being able to predict the probability of occupational insertion of men and women, and inquire about the factors that influence this probability, is essential in order to understand gender gaps in the labor market, helping to improve the design and implementation of public policies with a gender perspective, with the final goal to achieve equality of opportunities. In this framework, the present work will seek to predict the probability of transition from unemployment to the employment in Argentina from 2003 to 2019, using the Permanent Household Survey, based on traditional prediction techniques and Machine Learning, with the objective to find the most robust model that achieves the highest level of accuracy.
Pese a su creciente participación en el mercado laboral, las mujeres que deciden salir a buscar un puesto de trabajo enfrentan mayores dificultades para alcanzarlo. La participación de las mujeres en la fuerza laboral es considerablemente menor, inclusive, de ingresar al mercado laboral la posibilidad de encontrar efectivamente un trabajo es también menor a la chance que tienen los varones de hacerlo (CIPPEC, 2019). Poder predecir la probabilidad de inserción ocupacional de varones y mujeres, e indagar sobre los factores que influyen sobre dicha probabilidad, resulta fundamental en pos de entender las brechas de género en el mercado laboral, contribuyendo a mejorar el diseño e implementación de políticas públicas con perspectiva de género, y en última instancia lograr una mayor igualdad de oportunidades. En este marco, el presente trabajo buscará predecir la probabilidad de transición del desempleo al empleo de desocupados en ¡ Argentina para los años 2003 a 2019, utilizando la Encuesta Permanente de Hogares, a partir de técnicas tradicionales de predicción y de Machine Learning, con el objetivo de encontrar el modelo más robusto que logre el menor error de predicción.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.