Abstract

With increased globalization and labor mobility, human resource reallocation across firms, industries and regions has become the new norm in labor markets. The emergence of massive digital traces of such mobility offers a unique opportunity to understand labor mobility at an unprecedented scale and granularity. While most studies on labor mobility have largely focused on characterizing macro-level (e.g., region or company) or micro-level (e.g., employee) patterns, the problem of how to accurately predict an employee's next career move (which company with what job title) receives little attention. This paper presents the first study of large-scale experiments for predicting next career moves. We focus on two sources of predictive signals: profile context matching and career path mining and propose a contextual LSTM model, NEMO, to simultaneously capture signals from both sources by jointly learning latent representations for different types of entities (e.g., employees, skills, companies) that appear in different sources. In particular, NEMO generates the contextual representation by aggregating all the profile information and explores the dependencies in the career paths through the Long Short-Term Memory (LSTM) networks. Extensive experiments on a large, real-world Linkedln dataset show that NEMO significantly outperforms strong baselines and also reveal interesting insights in micro-level labor mobility.

Original languageEnglish (US)
Title of host publication26th International World Wide Web Conference 2017, WWW 2017 Companion
PublisherInternational World Wide Web Conferences Steering Committee
Pages505-513
Number of pages9
ISBN (Electronic)9781450349147
DOIs
StatePublished - Jan 1 2019
Event26th International World Wide Web Conference, WWW 2017 Companion - Perth, Australia
Duration: Apr 3 2017Apr 7 2017

Other

Other26th International World Wide Web Conference, WWW 2017 Companion
CountryAustralia
CityPerth
Period4/3/174/7/17

Fingerprint

Personnel
Industry
Macros
Experiments

Keywords

  • Career move
  • Contextual LSTM
  • Embedding

ASJC Scopus subject areas

  • Software
  • Computer Networks and Communications

Cite this

Li, L., Yang, J., Jing, H., He, Q., Tong, H., & Chen, B. C. (2019). NEMO: Next career move prediction with contextual embedding. In 26th International World Wide Web Conference 2017, WWW 2017 Companion (pp. 505-513). International World Wide Web Conferences Steering Committee. https://doi.org/10.1145/3041021.3054200

NEMO : Next career move prediction with contextual embedding. / Li, Liangyue; Yang, Jaewon; Jing, How; He, Qi; Tong, Hanghang; Chen, Bee Chung.

26th International World Wide Web Conference 2017, WWW 2017 Companion. International World Wide Web Conferences Steering Committee, 2019. p. 505-513.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Li, L, Yang, J, Jing, H, He, Q, Tong, H & Chen, BC 2019, NEMO: Next career move prediction with contextual embedding. in 26th International World Wide Web Conference 2017, WWW 2017 Companion. International World Wide Web Conferences Steering Committee, pp. 505-513, 26th International World Wide Web Conference, WWW 2017 Companion, Perth, Australia, 4/3/17. https://doi.org/10.1145/3041021.3054200
Li L, Yang J, Jing H, He Q, Tong H, Chen BC. NEMO: Next career move prediction with contextual embedding. In 26th International World Wide Web Conference 2017, WWW 2017 Companion. International World Wide Web Conferences Steering Committee. 2019. p. 505-513 https://doi.org/10.1145/3041021.3054200
Li, Liangyue ; Yang, Jaewon ; Jing, How ; He, Qi ; Tong, Hanghang ; Chen, Bee Chung. / NEMO : Next career move prediction with contextual embedding. 26th International World Wide Web Conference 2017, WWW 2017 Companion. International World Wide Web Conferences Steering Committee, 2019. pp. 505-513
@inproceedings{f7e7f57d0032496fb0c2a830e59b7379,
title = "NEMO: Next career move prediction with contextual embedding",
abstract = "With increased globalization and labor mobility, human resource reallocation across firms, industries and regions has become the new norm in labor markets. The emergence of massive digital traces of such mobility offers a unique opportunity to understand labor mobility at an unprecedented scale and granularity. While most studies on labor mobility have largely focused on characterizing macro-level (e.g., region or company) or micro-level (e.g., employee) patterns, the problem of how to accurately predict an employee's next career move (which company with what job title) receives little attention. This paper presents the first study of large-scale experiments for predicting next career moves. We focus on two sources of predictive signals: profile context matching and career path mining and propose a contextual LSTM model, NEMO, to simultaneously capture signals from both sources by jointly learning latent representations for different types of entities (e.g., employees, skills, companies) that appear in different sources. In particular, NEMO generates the contextual representation by aggregating all the profile information and explores the dependencies in the career paths through the Long Short-Term Memory (LSTM) networks. Extensive experiments on a large, real-world Linkedln dataset show that NEMO significantly outperforms strong baselines and also reveal interesting insights in micro-level labor mobility.",
keywords = "Career move, Contextual LSTM, Embedding",
author = "Liangyue Li and Jaewon Yang and How Jing and Qi He and Hanghang Tong and Chen, {Bee Chung}",
year = "2019",
month = "1",
day = "1",
doi = "10.1145/3041021.3054200",
language = "English (US)",
pages = "505--513",
booktitle = "26th International World Wide Web Conference 2017, WWW 2017 Companion",
publisher = "International World Wide Web Conferences Steering Committee",

}

TY - GEN

T1 - NEMO

T2 - Next career move prediction with contextual embedding

AU - Li, Liangyue

AU - Yang, Jaewon

AU - Jing, How

AU - He, Qi

AU - Tong, Hanghang

AU - Chen, Bee Chung

PY - 2019/1/1

Y1 - 2019/1/1

N2 - With increased globalization and labor mobility, human resource reallocation across firms, industries and regions has become the new norm in labor markets. The emergence of massive digital traces of such mobility offers a unique opportunity to understand labor mobility at an unprecedented scale and granularity. While most studies on labor mobility have largely focused on characterizing macro-level (e.g., region or company) or micro-level (e.g., employee) patterns, the problem of how to accurately predict an employee's next career move (which company with what job title) receives little attention. This paper presents the first study of large-scale experiments for predicting next career moves. We focus on two sources of predictive signals: profile context matching and career path mining and propose a contextual LSTM model, NEMO, to simultaneously capture signals from both sources by jointly learning latent representations for different types of entities (e.g., employees, skills, companies) that appear in different sources. In particular, NEMO generates the contextual representation by aggregating all the profile information and explores the dependencies in the career paths through the Long Short-Term Memory (LSTM) networks. Extensive experiments on a large, real-world Linkedln dataset show that NEMO significantly outperforms strong baselines and also reveal interesting insights in micro-level labor mobility.

AB - With increased globalization and labor mobility, human resource reallocation across firms, industries and regions has become the new norm in labor markets. The emergence of massive digital traces of such mobility offers a unique opportunity to understand labor mobility at an unprecedented scale and granularity. While most studies on labor mobility have largely focused on characterizing macro-level (e.g., region or company) or micro-level (e.g., employee) patterns, the problem of how to accurately predict an employee's next career move (which company with what job title) receives little attention. This paper presents the first study of large-scale experiments for predicting next career moves. We focus on two sources of predictive signals: profile context matching and career path mining and propose a contextual LSTM model, NEMO, to simultaneously capture signals from both sources by jointly learning latent representations for different types of entities (e.g., employees, skills, companies) that appear in different sources. In particular, NEMO generates the contextual representation by aggregating all the profile information and explores the dependencies in the career paths through the Long Short-Term Memory (LSTM) networks. Extensive experiments on a large, real-world Linkedln dataset show that NEMO significantly outperforms strong baselines and also reveal interesting insights in micro-level labor mobility.

KW - Career move

KW - Contextual LSTM

KW - Embedding

UR - http://www.scopus.com/inward/record.url?scp=85060269542&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060269542&partnerID=8YFLogxK

U2 - 10.1145/3041021.3054200

DO - 10.1145/3041021.3054200

M3 - Conference contribution

AN - SCOPUS:85060269542

SP - 505

EP - 513

BT - 26th International World Wide Web Conference 2017, WWW 2017 Companion

PB - International World Wide Web Conferences Steering Committee

ER -