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
Smart Loan Recovery System
Segments borrowers by default risk and suggests a recovery approach
2-3 weeks build
Overview
A recovery desk tool built on public Lending Club loan data from Kaggle. An XGBoost model estimates each borrower's default risk, k-means groups borrowers by repayment behaviour, and a rule layer maps each segment to a suggested action such as a reminder, a restructuring offer or escalation. A Streamlit dashboard lets the team filter segments and track outcomes.
What makes it stand up
- 01Default-risk model with calibrated probabilities
- 02K-means borrower segmentation with elbow and silhouette analysis
- 03Transparent rules mapping segments to recovery actions
- 04SHAP explanations for every individual risk score
- 05Recovery dashboard with segment filters and case notes
Module breakdown
- 01
Data prep
Cleans loan records and builds repayment features.
- 02
Risk model
XGBoost classifier with probability calibration.
- 03
Segmentation
K-means clusters profiled and named.
- 04
Strategy rules
Configurable mapping from segment to action.
- 05
Dashboard
Streamlit case view backed by PostgreSQL.
After this, you will be able to
- Explain how clustering and classification work together here
- Defend why the recovery rules stay human-readable
- Demo a borrower moving from score to suggested action
Technology stack
- Python
- Pandas
- scikit-learn
- XGBoost
- Streamlit
- PostgreSQL
- 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