Abstract: Recruitment is one of the most critical processes in human resource management, yet manual resume screening is time-consuming, costly, and prone to bias. Automated resume screening powered by machine learning offers a scalable solution to filter resumes efficiently and fairly. This study explores the development of an intelligent resume screening system using natural language processing (NLP) and supervised learning algorithms to classify resumes into relevant job categories. Data preprocessing techniques, such as tokenization, stopword removal, and TF-IDF vectorization, were employed to extract meaningful features from textual resumes. Models including Logistic Regression, Random Forest, and Support Vector Machines (SVM) were trained and evaluated on labelled datasets. The results demonstrated that machine learning-based screening achieved an accuracy of over 85% in categorizing resumes for IT roles (Software Developer, Data Analyst, Data Engineer). This research highlights the potential of machine learning to reduce HR workload, improve candidate-job matching, and minimize human bias, while also addressing ethical concerns such as fairness and transparency in AI-driven recruitment.

Downloads: | DOI: 10.17148/IARJSET.2025.12930