Phishing attacks are still very rampant and do not show signs of ever stopping. According to Santander Bank Customer Service, reports of phishing attacks have doubled each year since 2001. This work is based on identifying phishing Uniform Resource Locators (URLs). It focuses on preventing the issue of phishing attacks and detecting phishing URLs by using a total of 8 distinctive features that are extracted from the URLs. The sample size of study is 96,018 URLs. A total of four supervised machine learning algorithms: Naive Bayes Classifier, Support Vector Machine, Decision Tree and Random Forest were used to train the model and evaluate which of the algorithms performs better. Based on the analysis and evaluation, Random Forest performs best with an accuracy of 84.57% on the validation data set. The uniqueness of this work is in the choice of the selected features considered for the implementation.