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
SMS & Email Spam Classifier
TF-IDF and Naive Bayes spam filter with a paste-and-check web demo
1-2 weeks build
Overview
Trains a spam filter on the UCI SMS Spam Collection and a public email spam corpus. Messages are cleaned, tokenised and turned into TF-IDF vectors, then Multinomial Naive Bayes is compared with a linear SVM. A Flask page lets you paste any message and see the verdict along with the words that pushed it there.
What makes it stand up
- 01Text cleaning, stop-word removal and stemming with NLTK
- 02TF-IDF features with n-gram experiments
- 03Naive Bayes compared with a linear SVM
- 04Precision, recall and confusion matrix in the report
- 05Web demo that shows the most spam-like words in a message
Module breakdown
- 01
Datasets
Loads and merges SMS and email corpora with labels.
- 02
Preprocessing
Normalisation, tokenisation and stemming.
- 03
Vectorisation
TF-IDF with configurable n-gram range.
- 04
Classifiers
Naive Bayes and SVM trained and compared.
- 05
Web demo
Flask form returning a verdict and key words.
After this, you will be able to
- Explain Bayes' theorem and the naive independence assumption
- Defend why false positives matter more than false negatives here
- Demo the filter on messages the examiner types in
Technology stack
- Python
- scikit-learn
- NLTK
- Pandas
- Flask
- 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