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 Product Review Detection
Flags suspicious product reviews and tracks them on a moderation dashboard
2-3 weeks build
Overview
A review-moderation system trained on a public labelled fake-review dataset from Kaggle. It combines text features with behavioural signals such as review burstiness and rating deviation, compares a TF-IDF baseline with a fine-tuned DistilBERT, and routes flagged reviews to a dashboard where a moderator can confirm or clear them.
What makes it stand up
- 01TF-IDF logistic regression baseline against a fine-tuned DistilBERT
- 02Behavioural features: burst detection, rating deviation, reviewer history
- 03Moderation dashboard with confirm, clear and audit trail
- 04Confusion matrix and per-class F1 reported in the evaluation
- 05Explanations highlighting the words that drove each flag
Module breakdown
- 01
Data preparation
Cleans the labelled corpus and builds balanced splits.
- 02
Text models
Baseline classifier plus transformer fine-tuning.
- 03
Behaviour signals
Per-reviewer and per-product anomaly features.
- 04
Scoring API
Flask service returning a score and top contributing tokens.
- 05
Dashboard
React queue of flagged reviews with moderator actions.
After this, you will be able to
- Explain why text alone misses coordinated review campaigns
- Defend precision versus recall trade-offs for a moderation queue
- Demo a review being scored, flagged and cleared end to end
Technology stack
- Python
- scikit-learn
- Hugging Face Transformers
- Flask
- React
- MongoDB
- 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