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
Amazon Review Sentiment Analysis
Classifies product reviews as positive, negative or neutral
1-2 weeks build
Overview
Built on the public Amazon Fine Food Reviews dataset from Kaggle, this kit maps star ratings to sentiment labels, cleans and lemmatises the text, and compares a VADER baseline against TF-IDF models trained with logistic regression and Naive Bayes. The best model sits behind a small Flask page where you paste a review and see its label and the words that drove it.
What makes it stand up
- 01Star-rating to sentiment labelling with class-balance handling
- 02Text cleaning, lemmatisation and n-gram TF-IDF features
- 03VADER baseline against three trained classifiers
- 04Confusion matrix and per-class F1 in the report
- 05Flask demo showing the most influential words per prediction
Module breakdown
- 01
Data preparation
Deduplicates reviews and derives labels from star ratings.
- 02
Preprocessing
Tokenises, removes noise and lemmatises review text.
- 03
Modelling
Trains logistic regression, Naive Bayes and linear SVM.
- 04
Evaluation
Cross-validated F1, confusion matrices and error samples.
- 05
Web demo
Flask form that classifies a pasted review.
After this, you will be able to
- Explain how TF-IDF weights words and why n-grams help
- Defend your handling of the imbalanced rating classes
- Demo live predictions and justify a misclassified example
Technology stack
- Python
- Pandas
- scikit-learn
- NLTK
- 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