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
Fake News Detection with BERT
Transformer classifier with claim highlighting and source scoring
2-3 weeks build
Overview
A fine-tuned transformer that classifies news articles as reliable or misleading, highlights the spans that drove the decision using SHAP, and cross-checks the publishing source against a credibility index.
What makes it stand up
- 01Fine-tuned BERT baseline with an LSTM comparison
- 02SHAP token attributions rendered inline in the article
- 03Source credibility scoring from a curated registry
- 04Paste-text and fetch-by-URL input modes
- 05Ablation study comparing four model variants
Module breakdown
- 01
Data
Corpus assembly, de-duplication and stratified splits.
- 02
Modelling
Fine-tuning loop, scheduler and early stopping.
- 03
Explainability
SHAP values mapped back to tokens.
- 04
App
Streamlit interface with verdict and evidence.
- 05
Benchmarks
Model comparison table and error analysis.
After this, you will be able to
- Explain attention and why BERT outperforms bag-of-words
- Present a credible ablation study
- Discuss dataset bias honestly
Technology stack
- Python
- PyTorch
- Hugging Face
- Streamlit
- SHAP
- Level
- Major Project
- Domain
- Machine Learning
- Build time
- 2-3 weeks
- Difficulty
- Rating
- 4.6 / 5 · 176
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