Resume Screener using NLP
An application that screens an uploaded resume and predicts the type of the job depending on the keywords extracted from the document.
Case Study
Problem: Recruiters and hiring managers receive hundreds of resumes, making manual screening slow and error-prone.Traditional keyword matching often overlooks context, leading to inaccurate classification of resumes.There was a need to practice NLP techniques by building a system that could extract key terms and map them to job categories.The project aimed to demonstrate how AI can reduce repetitive HR tasks and speed up candidate shortlisting.
Approach: Developed a Streamlit web application for uploading and screening resumes in real time.Preprocessed text with tokenization, stop-word removal, and lemmatization to standardize resume content.Applied NLP and ML techniques (TF-IDF, classifiers) to identify relevant keywords and predict job categories.Designed a simple HTML/Streamlit UI for uploading resumes and displaying screening results.
Impact: Automated the initial resume screening process, reducing the effort required for manual shortlisting.Provided consistent classification of resumes into job types based on extracted keywords.Demonstrated practical use of NLP for real-world HR tech applications.Enhanced understanding of end-to-end ML workflows — from preprocessing to deployment with Streamlit.