Intelligent applicant tracking: leveraging machine learning for recruitment automation

Recruitment is a crucial, time consuming process in talent acquisition, which begins with the scouring of the talent pool in pursuit of the best candidates. In traditional applicant tracking systems (ATS), searching is usually based on keywords, which could result in any system that filters out applications using these keywords leading to a biased or an inefficient shortlisting. In this research, we explore the development of an intelligent applicant tracking system using ML to automate the recruitment process. In the proposed system, natural language processing (NLP) is used to analyze and rank resumes based on the job description, skill relevance and experience alignment. The candidate suitability prediction and hidden patterns in applicant data are predicted by advanced ML algorithms such as ensemble method such as catboost. The system is able to predict resume effectiveness through an ensemble learning models trained on a wide variety of resumes and generate actioned insights. In general, KNN model has proved itself to be effective in automating resume screening process by 92.5% accuracy. The developed system is both accurate, and explains what leads to model decisions, giving