International Research Journal of Education and Technology

Online recruitment platforms have made job searching easier, but they have also increased the number of fraudulent job postings. Recruitment scams often target job seekers by offering fake job opportunities and requesting money or sensitive information. Identifying such scams manually is difficult because fraudulent messages are written in a convincing way. This paper proposes an Intelligent Recruitment Scam Detection System that uses Machine Learning techniques to classify job descriptions as Scam or Real.

 The proposed system uses Count Vectorizer for text feature extraction and the Naive Bayes algorithm for classification. The model learns patterns from historical job description data and predicts the authenticity of new job postings. The system is implemented using Python and deployed with a Streamlit interface to provide an interactive and user-friendly experience. The results demonstrate that the Naive Bayes classifier performs efficiently for text-based scam detection tasks. The proposed solution offers a reliable, fast, and practical approach to protect users from recruitment fraud.

Keywords:Recruitment Scam Detection, Online Job Fraud Detection, Machine Learning, Supervised Learning, Naive Bayes Classifier, Probabilistic Classification, Count Vectorizer, Bag of Words Model, Text Classification, Natural Language Processing (NLP), Text Mining, Feature Extraction, Spam Detection, Fraud Detection System, Online Security, Cyber Security, Job Portal Safety, Data Preprocessing, Classification Model, Artificial Intelligence.