HYBRID DEEP LEARNING MODELS FOR ACCURATE ONLINE RECRUITMENT FRAUD DETECTION

Read full text Summarise with VIRAT
Authors: Journal of Digital Engineering and Business Management
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Hybrid deep learning models aid online employment scam detection. Because they use recurrent and convolutional neural networks, these systems can detect fraud. We can see patterns in user interactions and job ads in place and time. Advanced embedding and preprocessing can handle uneven and noisy datasets. This finding comes from combining company profiles and posting activities with job listing, email, and chat text. Due to the combination, it is now easier to discern ethical from immoral employment practices. Accuracy, recall, F1-score, and ROC-AUC are performance measurements. Experiments show these classifiers outperform machine learning leading models. Explainability tactics help people understand forecasts to build confidence. The system can automatically detect and inform users of scams on online job boards to boost trust.

Fields of Study & Subjects

Spam and Phishing Detection Cybercrime and Law Enforcement Studies Imbalanced Data Classification Techniques

Publication details

Journal / source
JDEBM
Publication date
26 March 2026
Language
EN