This study is motivated by the growing interest in cryptocurrency trading and the need for accurate forecasting tools to guide investment decisions. The main aim is to forecast price and trading volume changes of cryptocurrencies by determining their movement directions. Naïve Bayes, support vector machines, logistic regression, regression trees, and the K-nearest neighbors’ algorithm are selected to solve the problem and compared. Performance measures such as accuracy, sensitivity, and specificity are used to assess the models. The study shows that some models are better at predicting volume trends than price trends in cryptocurrencies. Naïve Bayes is good at spotting positive trends, while Logistic Regression is accurate at identifying negative trends. Interestingly, the research reveals that shorter prediction times are more accurate for price forecasts, but intermediate times work better for specificity. These insights help us understand which models work well for different aspects of cryptocurrency forecasting.