| dc.description.abstract | The purpose of this project is to create a job suggestion system for information technology (IT) professionals using K-means clustering algorithm, collaborative filtering techniques, and data from LinkedIn profiles.In this digital era, LinkedIn profiles are one of the main sources of professional information that can be used for job matching analysis. In this study, LinkedIn profiles, which include skills, work experience, and education, are analyzed to cluster users into homogeneous groups using the K-means algorithm. The clustering process begins with calculating the Euclidean distance between user profiles and the initial centroids to determine the nearest distance and establish the initial clusters. The average characteristics of the profiles inside each cluster are then calculated to update the centroids, and this process is continued until convergence is attained. Once the clusters are formed, the collaborative filtering method is used to provide suitable job recommendations based on profile similarities within the same cluster. The study's findings demonstrate that this method is highly accurate in providing suitable job recommendations, hence optimizing the fit between user qualifications and employment requirements in the IT industry. It is anticipated that the adoption of this recommendation system will aid employers in hiring qualified applicants and assist IT professionals in locating job possibilities that align with their qualifications and expertise. | en_US |
