 Fishing is a type of cyberattack where criminals impersonate legitimate organizations in order to steal personal data or money from unsuspecting victims. Recent advancements in machine learning algorithms have enabled researchers to develop more effective ways of detecting fishing websites. This paper compared four different machine learning algorithms, artificial neural networks, systems, support vector machines, SVMs, decision trees, DTs, and random forest, RF, to determine which was the most efficient at identifying fishing websites. The results showed that the random forest algorithm was the most accurate, outperforming all other approaches tested. This article was authored by Shook Al-Namari and Majid Al-Shammari.