International Journal of Scientific Research and Engineering Development

The rapid growth of online recruitment platforms has simplified job searching, but it has also increased the risk of fraudulent job advertisements that mislead applicants and exploit personal information. This study presents a machine learning-based Fake Job Post Prediction System to identify suspicious job postings using both textual and structured job-related attributes. The proposed framework incorporates advanced text preprocessing and feature extraction using TF-IDF, along with classification models such as PassiveAggressive Classifier and Multi-Layer Perceptron. To address class imbalance, the Synthetic Minority Oversampling Technique (SMOTE) is applied, improving the model’s ability to detect fraudulent cases. Experimental results on a publicly available dataset demonstrate enhanced performance compared to baseline approaches, with improved accuracy and reduced false positives. Furthermore, the system is integrated into a web-based application, enabling real-time prediction and user interaction. The proposed solution provides a scalable and efficient approach to enhancing trust and security in online recruitment systems.

Pranavi V. Armal, Suyash R. Tamkhane, Bhumi S. Parsawar, Aryan S. Rathod, Dr.R.R.Keole,"Fake Job Post Prediction System Using Machine Learning Approach" International Journal of Scientific Research and Engineering Development, V9(2): Page(1842-1848) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.