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 · Major Project
Liver Cirrhosis Stage Prediction
Compares classic ML and a neural network on clinical cirrhosis data
2-3 weeks build
Overview
Predicts histological cirrhosis stage from the Mayo Clinic primary biliary cirrhosis records published on Kaggle, using bilirubin, albumin, prothrombin time and other lab values. Random forest, XGBoost and a small neural network are trained on the same folds so the report can compare them fairly.
What makes it stand up
- 01Mayo Clinic PBC clinical dataset with a documented feature set
- 02Same cross-validation folds for every model for a fair comparison
- 03Tree ensembles versus a feed-forward neural network
- 04SHAP explanations of which lab values drive each stage
- 05Academic screening prototype, not a diagnostic tool
Module breakdown
- 01
Data cleaning
Imputation, encoding and outlier review.
- 02
Classic ML
Random forest and XGBoost with tuned hyperparameters.
- 03
Neural network
Keras multi-layer model with dropout and early stopping.
- 04
Comparison
Per-class F1, confusion matrices and training cost.
- 05
Demo app
Streamlit form with stage prediction and SHAP chart.
After this, you will be able to
- Explain why tree ensembles often beat neural nets on tabular data
- Defend your fair-comparison protocol across models
- Demo predictions with per-feature explanations
Technology stack
- Python
- scikit-learn
- XGBoost
- TensorFlow
- Pandas
- Streamlit
- Level
- Major Project
- Domain
- Machine Learning
- Build time
- 2-3 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