Resume Screening with Natural Language Processing (NLP)

This study addresses the difficulties employers face in screening the large number of resumes received for job positions. We aim to ensure fair evaluation of candidates, reduce bias, and increase the efficiency of the candidate evaluation process by automating the resume screening process. The proposed system uses NLP techniques to extract the relevant competencies from the resumes, focusing on the key skills required for specific positions. The competency sets taken for the positions were used. A case study was conducted for 123 job positions. Jaccard Similarity and Cosine Similarity measures were evaluated for the purposes of the study. Due to the fact that Cosine Similarity focuses on word frequency, Jaccard Similarity measure generates results more aligned with the purposes of the study. The extracted competencies are matched to predefined skill sets associated with various job positions using Jaccard Similarity. This approach assigns a similarity score to rank candidates by analyzing the presence or absence of specific words in their resumes in relation to the required competencies. This NLP-based system offers significant benefits such as saving time and other resources, increasing accuracy in candidate selection, and reducing bias by focusing only on competencies. The system's integration with LinkedIn enhances the effectiveness of the approach by facilitating seamless importation and analysis of resumes. Overall, this study demonstrates the potential of NLP in optimizing the resume screening process by providing a scalable, efficient, and unbiased solution for large organizations.