Streamlining Job Search and Detecting Fraudulent Job Listing

In today’s job market to explore how various contextual factors influence the accuracy of automatically detecting online recruitment fraud, this study seeks to highlight the significance of tailoring such fraud detection methods to local contexts. To achieve these goals, the study initially creates a dataset using a local and semi-structured advertising platform. This dataset is then utilized to train a machine learning model, which considers a range of content-based and contextual features. The study’s findings indicate that the incorporation of contextual features enhances the performance of automated online recruitment fraud detection models. The practical implications of this research are twofold. First, the contextual feature generation engine can be applied to diverse data-sets with minimal localization efforts. Second, these machine learning models can be integrated into online job recruitment platforms to identify and prevent online recruitment fraud.