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
Brain Stroke Risk Prediction
Predicts stroke risk from health records with imbalance handling
1-2 weeks build
Overview
Uses the public Kaggle stroke prediction dataset, where stroke cases are a small minority, to show why accuracy is the wrong metric. The kit compares class weighting, SMOTE and undersampling on the same models, reports precision-recall curves, and wraps the chosen model in a simple risk form.
What makes it stand up
- 01Public Kaggle stroke dataset with age, glucose, BMI and history
- 02Class weighting, SMOTE and undersampling compared directly
- 03Precision-recall curves and threshold tuning in the report
- 04SMOTE applied inside cross-validation folds to avoid leakage
- 05Academic risk-screening prototype, not medical advice
Module breakdown
- 01
Exploration
Class balance, missing BMI values and feature trends.
- 02
Preprocessing
Imputation, encoding and scaling in a pipeline.
- 03
Imbalance handling
Three resampling strategies on shared folds.
- 04
Evaluation
Recall, precision, F1 and PR-AUC per strategy.
- 05
Risk form
Streamlit page returning a risk band with explanation.
After this, you will be able to
- Explain why a 95% accurate model can miss every stroke
- Defend resampling inside folds rather than before splitting
- Demo threshold changes trading precision for recall
Technology stack
- Python
- scikit-learn
- imbalanced-learn
- Pandas
- 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