An ML-based Resume Screening and Ranking System

Abstract

In today's job market, resumes have flooded businesses, and the recruitment process has become an imposing task for companies. The traditional ways of resume screening are time-consuming and biased. To address these challenges, this research paper proposes a solution to automate this process through machine learning techniques. Based on existing research in this field, the aim is to improve the efficiency and accuracy of selecting candidates that are best suited for each job role without the use of complex techniques and provide equally good results. Existing methods involve the use of NLP, ML, and AI techniques to perform the screening process, each having its own advantages and disadvantages. Different ML models like SVM, Naive Bayes, and XGBoost have been explored and compared to find the most suitable and accurate approach. To improve accessibility and to implement a user-friendly system, a web application has also been created. On comparing the performance of these models using various performance metrics such as accuracy, precision, and F1 score, XGBoost is found to be the most suitable model with 0.89 AUC-ROC value and is used in the web application. As a novel approach, the candidates’ resumes are assigned scores based on the user's requirements and then ranked enabling the recruiter to shortlist suitable candidates for the job. This approach aims to simplify the resume screening process and revolutionize the hiring process.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 16 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.