Fake Job Listing Analysis Domain: Machine Learning

Abstract

Employment fraud is one of the most severe concerns addressed in the sphere of Online Recruitment Frauds in recent years. Many organizations these days like to list their job openings online so that job seekers may access them quickly and simply. However, this could be a form of scam perpetrated by con artists who offer job seekers work in exchange for money. For damaging a reputable company's credibility, fraudulent job adverts can be posted. These fraudulent job posting detections have sparked interest in developing an automated method for detecting phoney jobs and reporting them to the appropriate authorities. In order to det1ect bogus posts, a machine learning approach is used, which employs numerous categorization algorithms. A classification tool is used to separate bogus job postings from a wider set of job adverts in this scenario. To start, supervised learning algorithms as classification techniques are being studied to address the challenge of recognizing scammers on job postings. A classifier uses training data to map input variables to target classes. The paper's classifiers for distinguishing phone job postings from the others are briefly presented. These classifiers based prediction is classified into two types – Single classifier based prediction and ensemble classifier based prediction.