It is hard to trust any data entry on online websites as some websites may be malicious, and gather data for illegal or unintended use. For example, bank login and credit card information can be misused for financial theft. To make users aware of the digital safety of websites, we have tried to identify and learn the pattern on a dataset consisting of features of malicious and benign websites. We treated the problem of differentiation between malicious and benign websites as a classification problem and applied several machine learning techniques, for example, random forest, decision tree, logistic regression, and support vector machines to this data. Several evaluation metrics such as accuracy, precision, recall, F1 score, and false positive rate, were used to evaluate the performance of each classification technique. Since the dataset was imbalanced, the machine learning models developed a bias during training toward a specific class of websites. Multiple data balancing techniques, for example, undersampling, oversampling, and SMOTE, were applied for balancing the dataset and removing the bias. Our experiments showed that after balancing the data, the random forest algorithm using the oversampling technique showed the best results in all evaluation metrics for the benign and malicious website feature dataset.