Deep Learning based Detection of Fraud in Online Recruitment

Abstract

Concerned citizens might be reassured that this research examines a deep learning method for identifying fraud in online recruitment. Traditional systems for spotting rising fraud trends predominantly depend on rule-based screening, rendering them susceptible. In comparison to alternative methods, deep learning models, especially CNNs and RNNs, exhibit superior performance in identifying bogus job advertisements. The research utilizes a database of real and fabricated job adverts to derive pertinent textual and metadata for categorization objectives. A hybrid deep learning model integrates an attention mechanism with LSTM techniques to improve detection accuracy. The experimental findings indicate that the proposed model surpasses existing machine learning techniques in accuracy and reliability. The model's stability and generalizability are assessed through multiple datasets. Researchers may explore explainable AI systems for fraud detection in the future. This research significantly aids in the development of dependable online job boards.