slvDev
Featured
esp32-ai
A 28.9 million parameter language model runs on an $8 ESP32-S3 microcontroller entirely on-device, generating simple stories at about 9.5 tokens per second.
AI repository intelligence
FR-AI / ANALYSISWhy it is worth attention
It offers a practical, open-source solution for automating candidate shortlisting with interpretable scoring, reducing manual screening effort.
Who it is for
- Recruiters and HR professionals
- Small-to-medium businesses without expensive ATS
- Developers building recruitment automation tools
- Data science learners exploring NLP applications
Use cases
- Screening large volumes of resumes for a job opening
- Quickly identifying top candidates based on skill matching
- Generating ranked shortlists for hiring managers
- Learning how TF-IDF and cosine similarity apply to resume analysis
Strengths
- Combines TF-IDF similarity with explicit skill matching for a composite score
- Supports multiple file formats (PDF, DOCX, TXT)
- Built with Python and Streamlit for an accessible, interactive dashboard
- Categorizes candidates into clear match levels for easy decision-making
Considerations
- Relies on simple TF-IDF rather than advanced models like BERT
- Does not extract education or experience automatically
- Skill matching depends on predefined skill lists rather than deep semantic understanding
README quick start
AI Resume Screening System – Project Description
The AI Resume Screening System is an intelligent recruitment automation application designed to simplify and improve the process of screening job applicants. The system allows recruiters to upload multiple resumes in formats such as PDF, DOCX, and TXT and provide a Job Description (JD) for a specific position.
The system uses Natural Language Processing (NLP) and Machine Learning techniques to extract and analyze the content of resumes. It identifies relevant skills, compares the candidate's resume with the job description using TF-IDF and Cosine Similarity, and calculates a skill-matching score based on the required skills.
A final candidate score is generated by combining the AI-based resume similarity score and the skill-matching score. Based on the final score, candidates are categorized as Strong Match, Moderate Match, or Low Match. The system then ranks all applicants and displays the most suitable candidates for the given job role.
The application is developed using Python and Streamlit, with libraries such as Scikit-learn, Pandas, NumPy, PyPDF, and python-docx. The system provides recruiters with a user-friendly dashboard to view candidate rankings, matched skills, experience, similarity scores, and recommendations.
The main objective of this project is to reduce manual resume screening time, improve the efficiency of candidate shortlisting, and provide a consistent data-driven approach to recruitment. The system can be further enhanced using advanced NLP models such as BERT or Sentence Transformers, automated education and experience extraction, and an explainable AI-based candidate evaluation system.
Description
AI Resume Screening System: Developed an AI-powered application using Python, Streamlit, Scikit-learn, Pandas, and NLP to analyze resumes and rank candidates based on job-description relevance.
Related repositories
Similar projects matched by category, topics, and programming language.
gavamedia
Featured
deltafin
Deltafin is a research project that runs the 2.8-trillion-parameter Mixture-of-Experts model Kimi K3 on a single Apple Silicon Mac (e.g., M1 Max with 64 GB) at about 16 seconds per token, using exact, reproducible inference with local or streaming expert loading.
jamesob
Featured
local-llm
A comprehensive guide for building and configuring a high-end local machine to run state-of-the-art LLMs, with detailed hardware choices, BIOS tuning, and Docker-based model serving.