Find My Next Job

Labor Market Recommendations Using Administrative Big Data

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

Labor markets are undergoing change due to factors such as automatization and globalization, motivating the development of occupational recommender systems for jobseekers and caseworkers. This study generates occupational recommendations by utilizing a novel data set consisting of administrative records covering the entire Danish workforce. Based on actual labor market behavior in the period 2012-2015, how well can different models predict each users’ next occupation in 2016? Through offline experiments, the study finds that gradient-boosted decision tree models provide the best recommendations for future occupations in terms of mean reciprocal ranking and recall. Further, gradient-boosted decision tree models offer distinct advantages in the labor market domain due to their interpretability and ability to harness additional background information on workers. However, the study raises concerns regarding trade-offs between model accuracy and ethical issues, including privacy and the social reinforcement of gender divides.
Original languageEnglish
Title of host publicationThirteenth ACM Conference on Recommender Systems
Number of pages5
PublisherAssociation for Computing Machinery
Publication date2019
ISBN (Print)978-1-4503-6243-6/19/09
DOIs
Publication statusPublished - 2019

Cite this

Frid-Nielsen, S. S. (2019). Find My Next Job: Labor Market Recommendations Using Administrative Big Data. In Thirteenth ACM Conference on Recommender Systems Association for Computing Machinery. https://doi.org/10.1145/3298689.3346992
Frid-Nielsen, Snorre Sylvester. / Find My Next Job : Labor Market Recommendations Using Administrative Big Data. Thirteenth ACM Conference on Recommender Systems. Association for Computing Machinery, 2019.
@inproceedings{cec186dde318416f9b254cf95525b7af,
title = "Find My Next Job: Labor Market Recommendations Using Administrative Big Data",
abstract = "Labor markets are undergoing change due to factors such as automatization and globalization, motivating the development of occupational recommender systems for jobseekers and caseworkers. This study generates occupational recommendations by utilizing a novel data set consisting of administrative records covering the entire Danish workforce. Based on actual labor market behavior in the period 2012-2015, how well can different models predict each users’ next occupation in 2016? Through offline experiments, the study finds that gradient-boosted decision tree models provide the best recommendations for future occupations in terms of mean reciprocal ranking and recall. Further, gradient-boosted decision tree models offer distinct advantages in the labor market domain due to their interpretability and ability to harness additional background information on workers. However, the study raises concerns regarding trade-offs between model accuracy and ethical issues, including privacy and the social reinforcement of gender divides.",
author = "Frid-Nielsen, {Snorre Sylvester}",
year = "2019",
doi = "10.1145/3298689.3346992",
language = "English",
isbn = "978-1-4503-6243-6/19/09",
booktitle = "Thirteenth ACM Conference on Recommender Systems",
publisher = "Association for Computing Machinery",

}

Frid-Nielsen, SS 2019, Find My Next Job: Labor Market Recommendations Using Administrative Big Data. in Thirteenth ACM Conference on Recommender Systems. Association for Computing Machinery. https://doi.org/10.1145/3298689.3346992

Find My Next Job : Labor Market Recommendations Using Administrative Big Data. / Frid-Nielsen, Snorre Sylvester.

Thirteenth ACM Conference on Recommender Systems. Association for Computing Machinery, 2019.

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

TY - GEN

T1 - Find My Next Job

T2 - Labor Market Recommendations Using Administrative Big Data

AU - Frid-Nielsen, Snorre Sylvester

PY - 2019

Y1 - 2019

N2 - Labor markets are undergoing change due to factors such as automatization and globalization, motivating the development of occupational recommender systems for jobseekers and caseworkers. This study generates occupational recommendations by utilizing a novel data set consisting of administrative records covering the entire Danish workforce. Based on actual labor market behavior in the period 2012-2015, how well can different models predict each users’ next occupation in 2016? Through offline experiments, the study finds that gradient-boosted decision tree models provide the best recommendations for future occupations in terms of mean reciprocal ranking and recall. Further, gradient-boosted decision tree models offer distinct advantages in the labor market domain due to their interpretability and ability to harness additional background information on workers. However, the study raises concerns regarding trade-offs between model accuracy and ethical issues, including privacy and the social reinforcement of gender divides.

AB - Labor markets are undergoing change due to factors such as automatization and globalization, motivating the development of occupational recommender systems for jobseekers and caseworkers. This study generates occupational recommendations by utilizing a novel data set consisting of administrative records covering the entire Danish workforce. Based on actual labor market behavior in the period 2012-2015, how well can different models predict each users’ next occupation in 2016? Through offline experiments, the study finds that gradient-boosted decision tree models provide the best recommendations for future occupations in terms of mean reciprocal ranking and recall. Further, gradient-boosted decision tree models offer distinct advantages in the labor market domain due to their interpretability and ability to harness additional background information on workers. However, the study raises concerns regarding trade-offs between model accuracy and ethical issues, including privacy and the social reinforcement of gender divides.

U2 - 10.1145/3298689.3346992

DO - 10.1145/3298689.3346992

M3 - Article in proceedings

SN - 978-1-4503-6243-6/19/09

BT - Thirteenth ACM Conference on Recommender Systems

PB - Association for Computing Machinery

ER -

Frid-Nielsen SS. Find My Next Job: Labor Market Recommendations Using Administrative Big Data. In Thirteenth ACM Conference on Recommender Systems. Association for Computing Machinery. 2019 https://doi.org/10.1145/3298689.3346992