• D Madhu Sai Eswar
• Dr. K G Chiranjeevi

Social networking platforms are vital for communication and information sharing but face rising threats from fake user profiles used for misinformation, identity theft, and fraud. Traditional detection methods struggle against the evolving tactics of malicious users. This work proposes a Hybrid Machine Learning Model combining Random Forest (RF), Support Vector Machine (SVM), and Gradient Boosting Machine (GBM) using a soft voting ensemble to distinguish genuine and fake profiles. The model analyzes behavioral, activity, and profile-based features such as posting frequency, follower–following ratio, and profile completeness. Experimental results show that the hybrid model outperforms individual classifiers with higher accuracy, precision, recall, and F1-score, demonstrating strong reliability and scalability for improving social network integrity.

FAKE PROFILE DETECTION ON SOCIAL NETWORKING USING HYBRID MACHINE LEARNING MODELS

" FAKE PROFILE DETECTION ON SOCIAL NETWORKING USING HYBRID MACHINE LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 11, page no.a753-a761, November-2025, Available :http://www.jetir.org/papers/JETIR2511087.pdf

" FAKE PROFILE DETECTION ON SOCIAL NETWORKING USING HYBRID MACHINE LEARNING MODELS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 11, page no. ppa753-a761, November-2025, Available at : http://www.jetir.org/papers/JETIR2511087.pdf