Web URLs Phishing Detection Model with Random Forest Algorithm

As internet users grow and technology evolves, so do the security risks, one example being phishing. Phishing is an attempt to obtain important information from someone, such as username, password, and other sensitive data, by providing a fake website that resembles the original. This research focuses on the problem of phishing website URLs that are increasing in number. Creating a model using an Algorithm that can detect phishing website URLs. The classification algorithm model that will be used in this research is Random Forest, which will be evaluated based on the confusion matrix value. The accuracy result is 99%. Second, the f1 score test result is 99.1%. The third result of recall testing is 99.3%. The last test result is a precision of 98.9%. With high accuracy, f1 score, recall, and precision values, the model created using the Random Forest algorithm can be applied well to applications in web URLs, phishing detecting, analyzing fake URL patterns, and identifying suspected links as fake web URLs.