The 2nd International Data Science for Human Capital Management (DSHCM) workshop

Collocated with ECML-PKDD 2018.

While most global economies have experienced steady job growth since the Great Recession in 2007-2008, many structural problems persist. Despite a record number of job openings, the issue of underemployment exists in many countries and has been attributed to the skills gap. The emergence of web and mobile job portals, online professional networks and training courses have further changed people’s behavior of job seeking, skill acquisition and professional development. At the same time, it’s paramount for companies to focus on talent management to ensure high levels of employee engagement and workforce performance. In a highly competitive job market, it’s also important to focus on reducing employee turnover which can have a detrimental effect on employee morale, project work and company expenses.

Human Capital Management (HCM) refers to the set of practices and systems that facilitate talent acquisition and management. It encompasses the areas of talent and labor market analytics, job advertising and distribution, professional social networks, candidate sourcing, tracking, onboarding, benefits administration and compliance. For stable labor markets and social welfare of communities, it is important to match employers with the right candidates, provide opportunities for reskilling of the labor force, and ensure that the (post-hire) workforce is engaged and productive. Along with the socially conscious aspects of HCM, there is also a large market opportunity: the market size for HCM is estimated to be $131 billion. HCM is an industry which traditionally has not received much attention from experts in data science and machine learning. With the democratization of machine learning and artificial intelligence, there is great opportunity to bring awareness of HCM to more experts in the ICDM community and tackle problems which can have a wide social impact on a global scale.

There are many recent successful applications of data mining and data science techniques to problems in the HCM domain. For e.g., Text classification for job title classification; Sequence labeling and statistical modeling approaches find application in resume and job parsing; Near-deduplication algorithms in concert with big data pipelines power many job aggregators; Graph mining for career pathing; Predictive analytics have been used to model employee flight risk and employee engagement; Ontology mining techniques help build knowledge graphs of human capital entities; Personalized search and semantic search help job seekers by understanding searcher intent and contextual meaning of terms in the recruitment domain; Recommender systems have been used for expertise search and job recommendations.

Sponsored by: TBD