Abstract: Shortlisting qualified candidates from a large pool of resumes is a difficult problem for recruiters in the current recruitment process. Manual screening and keyword matching are the mainstays of traditional resume shortlisting techniques, which might result in biased judgements and leave out qualified candidates. In order to improve the efficiency of the resume shortlisting procedure, we suggest a resume shortlisting model in this research that makes use of text processing methods and TF-IDF. Our suggested model performs better than conventional approaches, offering greater accuracy and fewer false positives, making it a more economical and effective recruitment process solution.

Keywords: Machine Learning, Text Processing, Natural Language Processing, Tokenization, TF-IDF.

PDF | DOI: 10.17148/IJARCCE.2023.12338

Open chat
Chat with IJARCCE