The exponential growth in Internet usage has led to a rise in cyberthreats, especially phishing attacks, where attackers pretend to be legitimate organizations to deceive users into revealing sensitive information such as login credentials and financial details. This study evaluates the effectiveness of various machine learning algorithms in detecting phishing URLs using a dataset of over 11,000 URLs with 30 distinct features. This after heavy preprocessing by means of cleaning the data, feature scaling and feature selection developed a number of models including logistic regression, decision trees, random forest, support vector machines (SVM), and ensemble techniques of gradient boosting and AdaBoost that were applied on metrics including accuracy, precision, recall, F1-score, and ROC-AUC, while the model Gradient Boosting Classifier, Ranking classifier was determined as the most suitable model by the end and which achieved the best accuracy by scoring 97.4%. This suggests that machine learning is an essential component of cybersecurity and that advancements in deep learning techniques and real-time adaptive models may be a good addition to phishing prevention strategies, ultimately protecting users and organizations from malicious threats online.