Title: Job recommendation model using association rule on applicants' contextualised data

Authors: Ayodeji O.J. Ibitoye; Adeyinka O. Abiodun; Adeoluwa M. Siyanbade; Tijesu O. Oladimeji; Christianah Titilope Oyewale

Addresses: School of Computing and Mathematical Science, University of Greenwich, London, UK ' Department of Computer Science, National Open University, Abuja, Nigeria ' Computer Science Programme, Bowen University, Nigeria ' Department of Computer Science, Dominican University, Nigeria ' School of Collective Intelligence, Mohammed VI Polytechnic University, Rabat, Morocco

Abstract: Globally, the growing number of graduates is outpacing the availability of job opportunities. Not all degree holders possess the desired skills that align with their obtained degree for employment purposes, Hence, applicants are faced with the challenges of determining, which skillsets and earned degree align with their desired job positions. Here, a job dataset of 26705 samples, which contained user profile, and job descriptions were mined in context through association rule to recommend applicants next job opportunity using distinct and optimal hyperparameter of high confidence, and lift set as thresholds on different runs for validation. Overall experiments and evaluations showed a stronger positive association between the antecedents and consequents over a higher lift value using association mining when compared with apriori mining. The research presented sample exploratory information as outputs, highlighting the potential of association rule mining in bridging the gap between applicants' skill sets, degrees and desired jobs.

Keywords: unemployment; job prediction; association rule; academic degree; employee's skillset.

DOI: 10.1504/IJSSS.2024.140454

International Journal of Society Systems Science, 2024 Vol.15 No.1, pp.1 - 10

Received: 08 Dec 2022
Accepted: 03 Sep 2023
Published online: 19 Aug 2024 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article