A Conceptual Framework of Career Move Recommendation System

Abstract

Nowadays, job recommendation systems are becoming more and more popular for job seekers to generate personalized job recommendations, but it is increasingly challenging as the techniques used are changing rapidly. Most of the existing job recommendation systems only consider the user’s interests, without consideration of the user’s skills, which can help them to make a career move. In this paper, the problem was addressed by applying the Design Science Research Methodology to propose an artefact. The proposed conceptual framework generates personalized job and skill recommendations for a career move. This framework consists of five main components: Data Collection and Processing, Skill Identification and Mapping, Recommendation Engines, Job Recommendation, and Skill Recommendation. The data collection component retrieves job descriptions and online courses, while the skill identification component categorizes and maps skills to different job titles. The recommendation engines utilize content-based and collaborative filtering techniques to generate personalized job and skill recommendations based on user profiles, preferences, and skills. The proposed framework aims to enhance job-matching efficiency and assist users in identifying the required skills for career moves. Future research directions include evaluating the framework’s effectiveness and incorporating the user’s skill proficiency weighting to determine reskilling and upskilling needs.