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 tocreate and share their professional profiles, to connect with others who sharesimilar professional aspirations and to explore new career opportunities. Theseplatforms however do not offer a long-term roadmap to guide career progressionand improve workforce employability. The career trajectories of OPN users canserve as a reference but they are not always optimal. A career plan can also bedevised through consultation with career coaches, whose knowledge may howeverbe limited to a few industries. To address the above limitations, we present anovel data-driven approach dubbed JobComposer to automate career path planningand optimization. Its key premise is that the observed career trajectories inOPNs may not necessarily be optimal, and can be improved by learning tomaximize the sum of payoffs attainable by following a career path. At itsheart, JobComposer features a decomposition-based multicriteria utilitylearning procedure to achieve the best tradeoff among different payoff criteriain career path planning. Extensive studies using a city state-based OPN datasetdemonstrate that JobComposer returns career paths better than other baselinemethods and the actual career paths.