JobComposer: Career Path Optimization via Multicriteria Utility Learning

With online professional network platforms (OPNs, e.g., LinkedIn, Xing, etc.) becoming popular on the web, people are now turning to these platforms to create and share their professional profiles, to connect with others who share similar professional aspirations and to explore new career opportunities. These platforms however do not offer a long-term roadmap to guide career progression and improve workforce employability. The career trajectories of OPN users can serve as a reference but they are not always optimal. A career plan can also be devised through consultation with career coaches, whose knowledge may however be limited to a few industries. To address the above limitations, we present a novel data-driven approach dubbed JobComposer to automate career path planning and optimization. Its key premise is that the observed career trajectories in OPNs may not necessarily be optimal, and can be improved by learning to maximize the sum of payoffs attainable by following a career path. At its heart, JobComposer features a decomposition-based multicriteria utility learning procedure to achieve the best tradeoff among different payoff criteria in career path planning. Extensive studies using a city state-based OPN dataset demonstrate that JobComposer returns career paths better than other baseline methods and the actual career paths.

[1]  Deepak Agarwal,et al.  Ranking Universities Based on Career Outcomes of Graduates , 2016, KDD.

[2]  Giuseppe Moscarini,et al.  Occupational and Job Mobility in the US , 2006 .

[3]  J. Mokyr.  The Oxford Encyclopedia of Economic History , 2003 .

[4]  Dirk Helbing,et al.  Migration of Professionals to the U.S. - Evidence from LinkedIn Data , 2014, SocInfo.

[5]  R. Topel,et al.  Job Mobility and the Careers of Young Men , 1988 .

[6]  Yi Zhang,et al.  Is it time for a career switch? , 2013, WWW.

[7]  F. Wilcoxon.  Individual Comparisons by Ranking Methods , 1945 .

[8]  Hui Xiong,et al.  Talent Circle Detection in Job Transition Networks , 2016, KDD.

[9]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[10]  Kaisa Miettinen,et al.  Nonlinear multiobjective optimization , 1998, International series in operations research and management science.

[11]  Wai Fong Boh,et al.  The Career Paths Less (or More) Traveled: A Sequence Analysis of IT Career Histories, Mobility Patterns, and Career Success , 2012, MIS Q..

[12]  Y. Rozanov.  Markov random fields , 1984 .

[13]  Hui Xiong,et al.  Learning Career Mobility and Human Activity Patterns for Job Change Analysis , 2015, 2015 IEEE International Conference on Data Mining.

[14]  Amy Nicole Langville,et al.  A Survey of Eigenvector Methods for Web Information Retrieval , 2005, SIAM Rev..

[15]  H. B. Mitchell.  Markov Random Fields , 1982 .

[16]  Luming Zhang,et al.  Fortune Teller: Predicting Your Career Path , 2016, AAAI.

[17]  Alok N. Choudhary,et al.  JobMiner: a real-time system for mining job-related patterns from social media , 2013, KDD.

[18]  Sylvia Fuller,et al.  Job Mobility and Wage Trajectories for Men and Women in the United States , 2008 .

[19]  Yu Lou,et al.  A Machine Learning Approach for Future Career Planning , 2010 .

[20]  Mitul Tiwari,et al.  Importance of First Steps in a Community for Growth, Diversity, and Engagement , 2016, WWW.

[21]  Anmol Bhasin,et al.  Modeling professional similarity by mining professional career trajectories , 2014, KDD.

[22]  Rajeev Motwani,et al.  The PageRank Citation Ranking : Bringing Order to the Web , 1999, WWW 1999.

[23]  Sean R Eddy,et al.  What is dynamic programming? , 2004, Nature Biotechnology.