Machine learning & NLP
AI Resume Screening System
A Python notebook that classifies resume text into professional categories using natural language processing and machine learning.
- Author
- Donamol Joseph
- Status
- Notebook implementation
- Year
- 2026
Built with
- Python
- Pandas
- NLTK
- scikit-learn
- XGBoost
- TF-IDF
How it works
Cleans resume text, removes stopwords and lemmatises words before extracting TF-IDF features. It compares Naive Bayes, Logistic Regression, Random Forest and XGBoost classifiers.
The result
The notebook evaluates predictions, tunes Logistic Regression and exports the model, vectoriser and label encoder. A web interface and PDF uploads are planned extensions.