Intelligent Recommendation Engine for Vacancy-Resume Matching Using Hybrid ML Methods

Abstract

In modern recruiting and talent management systems, there is a growing demand for automated tools that can analyze large volumes of vacancies and resumes and provide relevant recommendations to both employers and job seekers. Traditional rule-based systems and simple search engines do not take into account the multidimensional nature of professional characteristics, semantic relationships between skill descriptions, contextual elements, and personality factors. This paper proposes an intelligent mechanism for matching vacancies and resumes based on a hybrid approach that combines content analysis, semantic vector text representations, and machine learning. The model is built on the integration of TF-IDF, word/sentence embedding, and a classification algorithm trained on “resume-vacancy” pairs with labeled compatibility. The conceptual architecture of the system, the data processing workflow, and an example of relevance assessment are presented. This approach increases the accuracy of recommendations and reduces manual efforts at the initial stage of candidate filtering.