A Survey on Artificial Intelligence (AI) based Job Recommendation Systems

Abstract

Job recommendation systems are AI-powered platforms that aim to provide job seekers with personalized job recommendations based on their skills, experience, and preferences. However, these systems face several challenges such as dealing with sparse data, maintaining data privacy and security, overcoming bias and discrimination, and ensuring transparency and interpretability. Recent techniques used in job recommendation systems include deep learning, reinforcement learning, and knowledge graphs. These techniques help to address the challenges such as dealing with sparse data, improving the accuracy of recommendations, and ensuring transparency as well as interpretability. The results of this study also helps to improve the job search experience for job seekers, reduces the time taken to find suitable job opportunities, and increase job satisfaction. Consequently, the job recommender architecture serves as a mediator. Accordingly, this work presents a detailed comprehensive survey of several filtering, machine learning and deep learning techniques that has revolutionised job recommendation system. Multiple applications and the associated challenges with existing job recommendation system are also discussed briefly.