Hybrid Information Filtering Engine for Personalized Job Recommender System

Abstract

The recommendation system, also known as recommender system or recommendation engine/platform, is considered as an interdisciplinary field. It uses the techniques of more than one field. Recommender system inherits approaches from all of machine learning, data mining, information retrieval, information filtering and human-computer interaction. In this paper, we propose our value-added architecture of the hybrid information filtering engine for job recommender system (HIFE-JRS). We discuss our developed system’s components to filter the most relevant information and produce the most personalized content to each user. The basic idea of recommender systems is to recommend items for users to suit their interests. Similarly the project tends to recommend relevant jobs for job-seekers by utilizing the concepts of recommender systems, information retrieval and data mining. The project solves the problem of flooding job-seekers with thousands of irrelevant jobs which is a frustrating and time-wasting process to let job-seekers rely on their limited searching abilities to dig into tons of jobs for finding the right job.