Collaborative filtering algorithms for a job recommendation system built with a microservice architecture

This article presents the development of a recommender system for recruiting personnel and vacancies to improve the efficiency of the hiring process. The proposed system has integrated collaborative and hybrid filtering methods to provide personalized job recommendations. Collaborative filtering model has analyzed historical data, identifying patterns by detecting connections between user information and job content. Research methodology has included literature analysis, dataset preparation, developing and training the Alternating Least Squares (ALS) model, and effectiveness evaluation of the implemented collaborative filtering algorithm by accuracy and performance metrics. Another part of the research is focused on integrating the recommendation module into an existing job and candidate search system built using microservices.