Resume Analyzer

Inspiration

As students applying for internships and jobs, we realized it's hard to understand how well a resume matches a job description. Many people apply without knowing their fit or missing skills. We wanted to solve this with an intelligent analyzer that gives instant, accurate feedback.

What it does

Resume Analyzer takes a user's resume (PDF) and a job description (text or PDF) and performs a smart comparison. It: -Extracts the text from both documents. -Calculates a similarity score using NLP (cosine similarity). -Highlights missing keywords or skills in the resume based on the job role. -Gives feedback on how well the resume matches the job posting.

How we built it

We used the following tools and technologies: Streamlit – for building the interactive web app. PyMuPDF – to read and extract text from uploaded resume PDFs. Natural Language Processing (NLP) – to analyze and compare the resume content with job descriptions. Scikit-learn – for implementing cosine similarity between resume and job description. Python – for backend logic and integration.

Challenges we ran into

-Understanding how to extract clean text from PDFs (some formats were inconsistent). -Making the comparison accurate despite different writing styles in resumes and job descriptions. -Streamlit deployment issues like setting paths and handling GitHub repo setup.

Accomplishments that we're proud of

-Successfully created a working prototype in a short time. -Extracted and analyzed text from PDF resumes. -Applied NLP techniques without deep prior knowledge. -Built a clean and usable Streamlit interface. -Collaborated as a team and completed deployment steps.

What we learned

-How to work with PDF data using PyMuPDF. -How to implement text similarity using cosine similarity. -Streamlit app development and deployment on the cloud. -GitHub collaboration and version control.

What's next for Resume Analyzer

-Add skill recommendations using AI (e.g., if a skill is missing, suggest how to learn it).

Generate a detailed report: Strengths, Weaknesses, and Suggestions.
Support for multiple job descriptions at once (compare across companies).
Add options to download the feedback as a PDF. -Make it more secure for storing personal resumes and data.