Natural language processing / Case study
Automated Resume Insights
I built a Django-based resume parser using spaCy and NLTK to extract and organize skills, education, work experience and contact information.
Harshit Makwana
- My role
- Django application & NLP pipeline development
- Timeline
- 2022
- Focus
- Natural language processing
01 / Context
From unstructured resumes to information recruiters can review.
Resume screening requires recruiters to locate the same kinds of information across documents with different wording and structures. I built a parser to automate extraction and categorization, making that information easier to review.
02 / Ownership
What I built
- Developed the resume-parsing application in Django and incorporated NLP processing with spaCy and NLTK.
- Implemented extraction and categorization for skills, education, work experience and contact information.
- Connected the processing workflow to a usable application so recruiters could work with organized information instead of repeating manual extraction.
03 / Engineering
Technical approach
Separate extraction from interpretation
My implementation focused on turning resume text into organized fields. The NLP workflow identified key information and grouped it into categories that correspond to common recruitment review tasks.
Bring the workflow into Django
I integrated the parsing software into a Django application. The resulting workflow automated part of manual screening and made the extracted details available for recruiters to assess; the project centered on information preparation for human review.
04 / System view
Workflow at a glance
Resume information
Unstructured candidate content
NLP processing
spaCy and NLTK
Categorization
Skills, education, experience and contact details
Recruiter review
Organized information in a Django application
05 / Delivery
Outcomes
- Reported key-detail parsing accuracy
- ~95%
I achieved nearly 95% accuracy in parsing the key resume details evaluated in the project. The application automated extraction tasks so recruiters could spend more of their effort evaluating candidates.
This result describes resume-information parsing, not candidate ranking or hiring quality. The evaluation sample and scoring protocol are not published here.
Technologies & methods
- Python
- Django
- spaCy
- NLTK
- Natural language processing
