One of the most prevalent neurological conditions, epilepsy affects millions of people worldwide. Due to the health hazards it presents, the condition has always held an immense amount of significance in the biomedical community. Electroencephalography (EEG) can be used to diagnose it since it is characterized by recurring, unprovoked seizures. Analyzing the results of an EEG in order to identify epileptic seizures in their early phases is a crucial part of epilepsy research. EEG measures the electrical activity in the brain. So, there is need of effective and accurate seizure prediction systems, which aid epileptic patients to get appropriate and timely health care and attention, thereby, foremost the patients to have a better life quality. The ability to accurately identify the pre-ictal state enables the patient to take sufficient and adequate preventive measures beforehand. In this work, we proposed a model for predicting the epileptic seizures. On the proposed model, diverse machine learning approaches such as SVM, KNN, GNB, Decision Tree, Random Forest, ETC, GCB, and XGBoost are evaluated. To evaluate effectiveness of projected model, precision, recall, F1 score, and accuracy are utilized as a parameter. As a result, Gradient Boosting for classification and XGBoost are performing well on the projected model.