• T. Gopu
• Boda Siva Sampath
• PONNAGANTI YASO KRISHNA
• Manne Varun Sai Subrahmanyam

As a main entry point for phishing, malware distribution, and identity theft, bad URLs are becoming more and more prevalent, which is a serious danger to internet security. Because signature-based techniques are so often unsuccessful against threats that are changing quickly, traditional URL detection systems mostly rely on them. In order to improve harmful URL identification and classification, this research investigates the use of machine learning approaches. The system attempts to precisely and efficiently identify dangerous URLs by utilizing a blend of feature extraction techniques and cutting-edge machine learning algorithms. The research includes gathering and preprocessing a variety of URL datasets, training and assessing many machine learning models, and feature engineering to capture important attributes that differentiate harmful from benign URLs. In particular, we apply sentiment analysis to identify possible malicious URLS using Random Forest, XG Boost, Light GBMs algorithms. These algorithms were selected because they work well with big datasets and can identify trends that point to fraudulent activity. When accuracy is used to evaluate algorithm performance, Random Forest comes out on top, with an impressive accuracy percentage of 96.30% among the algorithms examined. Nonetheless, the XG Boost, Light GBM algorithms also perform admirably, with accuracy rates of 94.5% respectively.

: Blacklists, Random Forest, XG Boost, Light GBM Classifier, Performance evaluation, Accuracy.

"Evaluating the authenticity of urls using random forest algorithm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 12, page no.b164-b168, December-2024, Available :http://www.jetir.org/papers/JETIR2412108.pdf

"Evaluating the authenticity of urls using random forest algorithm", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 12, page no. ppb164-b168, December-2024, Available at : http://www.jetir.org/papers/JETIR2412108.pdf