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
Parkinson's Disease Detection from Voice
Classifies Parkinson's markers from sustained-vowel voice features
1-2 weeks build
Overview
Uses the UCI Parkinson's dataset of jitter, shimmer and noise-ratio measurements to train and compare several classifiers. Evaluation is split by subject so recordings from one person never leak across train and test, and a Streamlit page lets examiners try feature values interactively.
What makes it stand up
- 01UCI Parkinson's voice dataset with a documented feature glossary
- 02Subject-wise cross-validation to avoid recording-level leakage
- 03Comparison of logistic regression, SVM, random forest and XGBoost
- 04Feature-importance plots linking results to vocal biomarkers
- 05Academic screening prototype, not a diagnostic tool
Module breakdown
- 01
Data exploration
Distributions, correlations and class balance per feature.
- 02
Preprocessing
Scaling, subject grouping and train-test splitting.
- 03
Model training
Four classifiers tuned with grouped grid search.
- 04
Evaluation
Confusion matrix, ROC curves and per-class F1 in the report.
- 05
Demo app
Streamlit form that scores a feature vector with explanations.
After this, you will be able to
- Explain what jitter and shimmer measure in a voice signal
- Defend subject-wise splitting against a random split
- Demo predictions and feature importance in Streamlit
Technology stack
- Python
- scikit-learn
- XGBoost
- 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