مشخصات پژوهش

عنوان	An Evaluation of Collaborative-Filtering Algorithms for Job Recommender Systems
نوع پژوهش	مقاله ارائه شده
کلیدواژه‌ها	Recommender system, e-recruitment, job, machine learning, Collaborative-Filtering
چکیده	At present, there has been a significant increase in job opportunities in the business sector. In order to adapt to the current societal and international conditions, these jobs need to transition towards digitalization in the online realm. The progression of technology indicates that businesses without an online presence are destined to fail or experience limited growth. As a result, this issue has given rise to the field of data mining and the study of job recommender systems utilizing the latest algorithms. In this study, we assess four collaborative filtering algorithms for a job recommender system. The findings reveal that the Cocluster method exhibits the least amount of error, while NMF(Non-negative matrix factorization) demonstrates the most efficient training time compared to the other algorithms.
پژوهشگران	آرش خسروی (نفر اول)، احمد آذرنیک (نفر دوم)