This study investigated the feasibility of using random forest classification to distinguish left and right movements based on electroencephalogram (EEG) data. EEG signals of brain activity were gathered in BCI competition signal 3a (Hand Movements) and a dataset containing eight data channels was created for each trial. A random forest model was trained on this data to classify the movement associated with each trial. A significance analysis was performed to determine the most suitable EEG channels for classification. The results show that random forest classification can effectively distinguish left and right movements and achieve high accuracy. This work demonstrates the potential of machine learning algorithms, particularly random forest, for EEG-based movements, paving the way for their use in brain-computer interfaces and neuro prosthetics.