gilangcowokull/SnifTern.ai
🐙 SnifTern.ai is an AI-powered internship fraud detection platform built with Flask. It uses machine learning to identify fake postings and verify company legitimacy.
What's novel
🐙 SnifTern.ai is an AI-powered internship fraud detection platform built with Flask. It uses machine learning to identify fake postings and verify company legitimacy.
Code Analysis
11 files read · 4 roundsA Flask web app that classifies internship job postings as fake or real using a TF-IDF + Logistic Regression model combined with regex-based fraud pattern matching, with basic web scraping, OCR, and PDF report generation.
Strengths
The hybrid ML + rule-based detection approach is practical for this domain, and the code is functional and readable with reasonable separation between preprocessing, prediction, scraping, and OCR modules.
Weaknesses
The README significantly overstates capabilities (claims multi-platform integration, comprehensive company database, multi-language NLP when it's actually naive CSS-selector scraping, 6 hardcoded companies, and UI string translation only); the codebase has dead code (Streamlit imports in a Flask app), a broken test import, no real test framework, and a monolithic app.py.
Score Breakdown
Signal breakdown
Innovation
Craft
Traction
Scope
Evidence
Commits
10
Contributors
2
Files
36
Active weeks
4
Repository
Language
Python
Stars
2
Forks
0
License
MIT