PopularMajor Project
Machine Learning
AI Resume Screening System
NLP pipeline that ranks candidates against a job description
- Python
- spaCy
- scikit-learn
- FastAPI
- +2
₹4,499₹7,999
4.9/214 reviews
Machine Learning · Mini Project
Binary Classification: Model Comparison Study
Four classic classifiers benchmarked properly on one public dataset
1-2 weeks build
Overview
A disciplined comparison of logistic regression, SVM, random forest and XGBoost on the UCI Bank Marketing dataset. Every model shares one preprocessing pipeline and stratified cross-validation, and the study reports ROC and precision-recall curves, calibration and a statistical test of whether the differences between models are real.
What makes it stand up
- 01One scikit-learn pipeline shared by all four models to avoid leakage
- 02Stratified k-fold cross-validation with hyperparameter search
- 03ROC-AUC, PR-AUC, F1 and calibration curves for every model
- 04McNemar's test to check whether model differences are significant
- 05Streamlit app to swap models and inspect their metrics live
Module breakdown
- 01
Pipeline
Scaling, encoding and imputation wrapped in one transformer.
- 02
Models
Logistic regression, SVM, random forest and XGBoost.
- 03
Tuning
Grid and randomised search inside cross-validation.
- 04
Metrics
Curves, confusion matrices and threshold selection.
- 05
Explorer app
Interactive comparison of models and thresholds.
After this, you will be able to
- Explain when accuracy misleads and which metric to use instead
- Defend why preprocessing must sit inside cross-validation
- Demo how moving the threshold trades precision for recall
Technology stack
- Python
- Pandas
- scikit-learn
- XGBoost
- Streamlit
- Level
- Mini Project
- Domain
- Machine Learning
- Build time
- 1-2 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support