Reciprocal Recommendation for Job Matching with Bidirectional Feedback

This paper proposes a novel reciprocal recommendation method for job matching with bi-directional feedback. The proposed method uses, as mutual feedback, bilateral messages between job seekers and recruiters, such as applying to a job, scout of a seeker, and reply to the offer, on the seekers-recruiters' user network. During job matching process, user agents, as delegate of their owners, send and receive those messages with each other. From those feedback messages, each user agent computes the popularity degree of its owner user: seeker or recruiter, and evaluation degree of each other from the popularity degree, considering both the popularity and evaluation degrees, and the similarity between a condition provided by its user and a profile of each candidate user, the agent dynamically updates a ranking list for recommendation of its owner user after every matching action. Preliminary experiments illustrate the validity of the proposed method.