Machine Learning Model to Selection of Job Applicant Documents to Increase The Human Resources Department Performance

The planning of the company's existing and future human resource needs is included in the process of human resource recruitment. The availability of human resources, in terms of both quality and quantity, will be significantly impacted by the recruitment process, if it is both efficient and successful. The initial stages of the employee recruitment process involve selecting applicant documents according to company needs. Currently, the document selection process is done manually by studying the applicant documents one by one and then grouping them into several categories. This mechanism is inefficient and risks producing the wrong choices. On the other hand, machine learning has text recognition and image processing capabilities to increase the effectiveness and efficiency of the process. So, the purpose of this research is to help companies, especially the human resources division, improve the effectiveness and efficiency of new employee selection, especially the selection and classification of job applicant documents. The research method uses a qualitative approach with a literature review to identify new employee recruitment problems was continued by designing data sets, training data, and testing with machine learning using the LVQ method. The result of this research is that a machine learning model builds a model for selecting job applicant documents using machine learning with the Learning Vector Quantization (LVQ) method.