Job Recommendation Systems

Abstract

On the Internet, the biggest problem for a person looking for a job online is not just knowing how to get enough information to make a decision, but also how to make a good decision from the huge amount of information. Recommender systems are widely used systems that provide real-time recommendations of relevant items to each user. Job recommendation systems play a key role in helping employees find the right opportunities and recruiters reaching top candidates. To do so, recommendations techniques such as collaborative fltering, content-based fltering, knowledge-based and hybrid approaches can be applied. In this thesis, we draw up a state of the art of existing works in the use of job rec- ommendation in two axes, the traditional job recommendation systems that focus on a single way of recommendation and the reciprocal job recommendation systems that help to match jobs to employees and employees to jobs, After that we will be comparing these works and synthesize them to have a global vision on this research axis, we will end up with moovWork platform which is an intelifox 's vision to the future of freelancing in Algeria, the project perspectives is to provide a platform for freelancers with better user experience and excellent performance including reciprocal recommendation using a hybrid recommender system based on content-based and interaction-based approaches.