A Machine Learning project to identify the spam job postings
archive.zip
The Employment Scam Aegean Dataset (EMSCAD)
http://emscad.samos.aegean.gr/
Dheera Shaji
Karthik Rayan V
Lakshman P
Vaishnavi R Nath
1. Cleaning of data using NLP techniques
2. Exploratory Data Analysis - Identified heavy class imbalance
3. Handling class imbalance
4. Different vectorization techniques - uni,bi,tri - gram and TF-IDF
5. Training and comparing several machine learning models