A1028
Title: Forecasting online job vacancy attractiveness
Authors: Stefan Lyocsa - Slovak Academy of Sciences (Slovakia) [presenting]
Miroslav Stefanik - Institute of Economic Research, Slovak Academy of Sciences (Slovakia)
Zuzana Kostalova - Slovak Academy of Sciences (Slovakia)
Abstract: The predictability of online job vacancies (OJVs) attractiveness by job seekers is explored: i) number of job ad views, ii) response and iii) conversion rate (the ratio of the two). Forecasting models utilize above 800 explanatory variables related to job characteristics, prerequisites and benefits, including simple textual features and even calendar effects. Apart from standard machine learning models, network-based feature extraction methods are used and whether the complex relationship between features of OJVs leads to improved forecasting of OJVs attractiveness is explored. The findings could help employers to better target prospective applicants and could be implemented in the search interface by the job portals to improve job matching, i.e. lead to improved recommender systems.
