📞 +91-7667918914 | ✉️ iarjset@gmail.com
International Advanced Research Journal in Science, Engineering and Technology
International Advanced Research Journal in Science, Engineering and Technology A Monthly Peer-Reviewed Multidisciplinary Journal
ISSN Online 2393-8021ISSN Print 2394-1588Since 2014
IARJSET aligns to the suggestive parameters by the latest University Grants Commission (UGC) for peer-reviewed journals, committed to promoting research excellence, ethical publishing practices, and a global scholarly impact.
← Back to VOLUME 13, ISSUE 10, OCTOBER 2026

An Explainable Machine Learning Approach for Detecting Fraudulent Online Job Postings

Sherkar Akanksha, Dhanore Vishakha, Thube Sakshi, Payal Ulhare

👁 12 views📥 6 downloads
Share: 𝕏 f in ✈ ✉
Abstract: Online recruitment platforms make it easier for applicants to discover vacancies, but they can also be misused by people posing as legitimate employers. Such schemes may seek advance fees, personal information, or other benefits from job seekers. Automated screening could help moderators prioritise advertisements that deserve closer inspection. A useful system should also provide reasons for its predictions, rather than returning a risk label alone. This paper outlines an explainable machine-learning workflow that combines advertisement text—including job titles, descriptions, requirements and company profiles—with structured posting attributes. The proposed process includes data auditing, text representation, leakage-aware data splitting, methods for addressing class imbalance, baseline classifiers, and post-hoc explanations with SHAP or LIME. Precision, recall, F1-score, PR-AUC and a confusion matrix are planned for evaluation. The Employment Scam Aegean Dataset (EMSCAD) is a candidate source, subject to checking the downloaded version and its usage conditions. Because implementation and testing have not yet been completed, this paper reports no measured performance. The intended outcome is a decision-support approach that makes evidence and uncertainty visible while keeping final judgements with human reviewers.

Keywords: online recruitment fraud, fake job postings, explainable AI, machine learning, natural language processing, SHAP, LIME, class imbalance

How to Cite:

[1] Sherkar Akanksha, Dhanore Vishakha, Thube Sakshi, Payal Ulhare, “An Explainable Machine Learning Approach for Detecting Fraudulent Online Job Postings,” International Advanced Research Journal in Science, Engineering and Technology (IARJSET)

Creative Commons License This work is licensed under a Creative Commons Attribution 4.0 International License.