Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{199817,
        author = {Riya Ranjit Mohanty and Varun Narendra Vangari and Mr.Ramakrishna Iyer},
        title = {Resume Job-Match Scorer (Cosine Similarity+NLP)},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {14514-14517},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=199817},
        abstract = {Recruiting the right candidate for a job opening is a resource-intensive task, and the manual screening of hundreds of resumes is prone to both inefficiency and bias. This paper presents a Resume–Job Match Scorer — an automated system that leverages Natural Language Processing (NLP) techniques alongside Term Frequency–Inverse Document Frequency (TF-IDF) vectorization and cosine similarity to quantify how well a given résumé aligns with a specific job description. The proposed system preprocesses both documents through a pipeline comprising tokenization, stop-word removal, and lemmatization, converts them into high-dimensional TF-IDF feature vectors, and then computes a normalized similarity score in the range [0, 1]. Experimental evaluation on a curated dataset of 200 resume–job pairs yield a Pearson correlation of 0.87 with human expert rankings, demonstrating that the approach is not only computationally efficient but also meaningful from a recruitment standpoint. The paper details the full methodology and provides a discussion of results, advantages, limitations, and directions for future research.},
        keywords = {cosine similarity, TF-IDF, natural language processing, resume screening, recruitment automation, text vectorization, job matching.},
        month = {April},
        }