An enhanced Hybrid Recommendation system for job Recruitment using Graph Based Approach
Background to the Study
Recommendation systems have demonstrated success in many online domains such as sales, media, and social com- munities by connecting users to the items of their interest and building their loyalty. With the excess of available online information, job seekers need to have access to relevant job openings in almost real-time, however, browsing through thousands of jobs for finding few relevant ones can be a tedious task for many applicants. With this motivation, our goal is to build an effective recommendation system to improve the job search process by harnessing multiple signals of relevance and providing job seekers (i.e. applicants) with personalized job recommendations. Collaborative filtering (CF) is one of the widely used recommendation approaches which exploits the user-item interactions to identify similar items (a.k.a. item- based CF) or users (a.k.a. user-based CF) and predict a user’s future interests.
With the increasing volume of information available online, recommender systems have become a daily tool for Internet users, providing them with desirable help in finding information. The recommender systems used to determine the interested items for a specific user by employing a variety of information resources that related to users and items. In the mid-1990s, the term recommender system was published for the first time in information system literature. Recommender systems are being broadly accepted in various applications to suggest products, services, and information items to latent customers. Many e-commerce applications joint recommender systems in order to expand customer services, increase selling rates and decrease customers search time. For example, a wide range of companies such as the online book retailer Amazon.com , books , news articles . Additionally, Microsoft provides users many recommendations such as the free download products, bug fixes and so forth. All these companies have successfully set up commercial recommender systems and have increased web sales and improved customer fidelity.
For many years, information system supports in human resource management have been mainly restricted in storing and tracking applicants’ data through the applicant management systems. These systems support the internal workflows and communication processes between the human resource management department and the other departments. Recently, the increased amount of digital information and the emergence of e-business reform the way companies conduct business in different aspects. Initially, simple solutions are applied such as posting the job ads on the career unit of the corporate website. Then, based on the experiences gained from these first implementations, the opportunities are realized establishing other changes and hence, implementing enhanced e-recruitment platforms.
The Internet-based online recruiting platform or e- recruitment platform is one of the most successful e-business changes, which changed the way companies employ candidates. These platforms spread in the recent years because the recruiting of the appropriate person is a challenge faced most companies, as well as the unavailability of certain candidates in some skill areas has long been identified as a major obstacle to companies success Laumer . The online channels like Internet job portal, social media applications or a firm’s career website have driven this development. While the companies established job positions on these portals, job-seeker uses them to publish their profiles. For each posted job, thousands of resumes received by companies. Consequently, a huge volume of job descriptions and candidate resumes are becoming available online. This vast volume of information gives a great opportunity for enhancing the matching quality; this potential is unused since search functionality in recruiting applications is mainly restricted to Boolean search method. The need increases for applying the recommender system technologies that can help recruiters to handle this information efficiently. Many researches have been conducted to discuss different issues related to the recruiting problem as well as, the applying of recommender system technologies. However, job recommendation is still a challenging domain and a growing area of research. In order to support this research area, we conduct a comprehensive study for job recommendation. We will discuss the e- recruitment problem and present the different issues related to applying recommender systems in candidates/job matching.