Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{186226,
        author = {Dr. S. S. Khatal and Miss. Tattu Minal Goraksh and Miss. Nawale Mahima Nanasaheb and Mr. Maval Vivek Sanjay},
        title = {An Intelligent Multi-Model Framework for Online Recruitment Fraud Detection Using Trust Score and Explainable AI : A Review},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {6},
        pages = {621-628},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=186226},
        abstract = {Online recruitment fraud has emerged as a significant cybersecurity concern, deceiving job seekers through fake advertisements, phishing emails, and fraudulent offers on digital platforms. This paper presents an Advanced Fake Job Post Detection System that leverages machine learning and trust-based analysis to accurately identify deceptive job postings in real time. The proposed framework integrates multiple models Multilayer Perceptron (MLP), Passive Aggressive Classifier, Gradient Boosting, and K-Nearest Neighbors allowing flexible and comparative prediction for enhanced reliability. Unlike traditional systems limited to static datasets, this model processes live job data and email inputs, including attachments, to determine authenticity. The system performs comprehensive data preprocessing involving text cleaning, encoding, and feature selection to focus on key attributes such as job description, company logo, education, and experience requirements. A Trust Score mechanism is introduced to quantify the credibility of each post, classifying them as suspicious, uncertain, or verified real, while an explanation report provides reasoning for each prediction. Furthermore, trend analysis visualizes the distribution of fake posts across platforms and job categories. The experimental results demonstrate that the proposed model achieves improved accuracy, faster processing, and practical applicability, offering a robust, transparent, and user-centric solution for mitigating online recruitment frauds and safeguarding job seekers.transparent, and user-centric solution for mitigating online recruitment frauds and safeguarding job seekers.},
        keywords = {Online Recruitment Fraud, Fake Job Post Detection, Machine Learning, Trust Score, Real-Time Classification, Feature Selection, Text Analytics, Gradient Boosting, Explainable AI, Cybersecurity.},
        month = {November},
        }