Detecting Fake Job Posting Using ML Classifications and Ensemble Model

Abstract

In this project, we create a fraudulent checker tool to detect fake job postings using NLP (Natural Language Processing) and ML approaches (Random Forest Classifiers, Logistic Regression, Support Vector Machines, and XGBoost Classifiers). These approaches will be compared and then combined into an ensemble model which is used for our job detector. The aim is to predict using machine learning for real or fake job prediction results with the highest accuracy. Dataset analysis is performed by supervised machine learning techniques (SMLT) and collects a variety of information such as variable identification, missing value handling, and data validation analysis. Data cleaning and preparation along with visualization are performed on the entire dataset. The ensemble model is created at the end using ML Algorithms like XGBoost, SVM, Logistic Regression, and Random Forest Classifier by choosing 4 of the best contributing features. The model produced at the end will be implemented in a Flask application for demonstration.