Analisis Kecocokan Profil Pelamar Kerja Dengan Bidirectional Encoder RepresentationFrom Transformers (Bert)

Ernanta, Dimas Mulya Perkasa (2024) Analisis Kecocokan Profil Pelamar Kerja Dengan Bidirectional Encoder RepresentationFrom Transformers (Bert). Diploma thesis, Politeknik Negeri Jember.

	Text (Abstract) Abstract.pdf - Submitted Version Available under License Creative Commons Attribution Non-commercial Share Alike. Download (40kB)
	Text (Daftar Pustaka) Daftar Pustaka.pdf - Submitted Version Available under License Creative Commons Attribution Non-commercial Share Alike. Download (80kB)
	Text (Laporan Lengkap) Laporan Lengkap.pdf Restricted to Registered users only Download (3MB) | Request a copy
	Text (Bab 1 Pendahuluan) Bab 1 Pendahuluan.pdf - Submitted Version Available under License Creative Commons Attribution Non-commercial Share Alike. Download (91kB)

Abstract

Talent Recruitment, also known as talent acquisition, is a critical process for organizations looking to attract and recruit the most qualified individuals to work for their company. It involves identifying, sourcing, and selecting talented individuals who have the skills, experience, and potential to contribute to the company's success. However, with the proliferation of online platforms such as job websites and professional social networks, the number of applicants that Companies have to review has drastically increased. The traditional manual process of reading and evaluating each CV and cover letter has become inefficient and time-consuming. Companies have to manually sort, compare and evaluate thousands of applicant data, which is prone to errors and can reduce the accuracy of selecting the right employees. Therefore, this research aims to improve accuracy in the talent recruitment process by applying the latest technology, namely the BERT model, which can analyze the suitability of job applicant profiles. The BERT model is proven to have the ability to process text data with high accuracy and is suitable for use in employee selection. The result of this research is that the CV evaluated using the BERT model produces an accuracy rate of 0.8 or 80% which can categorize applicants based on work experience, description and interests. Keywords : BERT, Data Mining, Curriculum Vitae, Machine Learning

Actions (login required)

View Item