DIGGING INTO VARIOUS WAYS TO IDENTIFY DECEPTIVE JOB POSTINGS

Abstract: Fake job postings as a important threat in the electronic job market, exploiting job seekers and compromising sensitive information. This comparative study aims to discover various machine learning algorithms and practices to find and predict fake job posts. The research involves analyzing a dataset of job postings, identifying features that distinguish legitimate from fraudulent job ads, and evaluating the efficiency of different classification models. In the end, this study offers a solid answer for boosting the security of online job marketplaces by shedding light on how well systems like Conclusion Trees, Haphazard Forest, Support Vector Machine (SVM), and Neural Networks perform in identifying false job posts.

Keywords: • Fake job postings • Job fraud detection • Machine learning • Classification models • Online job market • Data analysis • Feature extraction • Model evaluation