An epileptic seizure is a type of seizure induced by aberrant brain activity caused by an epileptic condition, which is a brain Central Nervous System disorder (CNS). CNSs are relatively prevalent and include a wide range of symptoms, including loss of awareness, and strange behaviour. These symptoms frequently result in injuries as a result of walking imbalance, tongue biting, and hearing loss. For many researchers, detecting a prospective seizure in advance has been a difficult undertaking. In this research work we have used non-imaging data and applied supervised learning algorithms to determine the classification of epilepsy and try to improve the efficiency of the model, compared to the existing ones. Random Forest algorithm was found to have highest accuracy compared to other machine learning models. The paper can be helpful in diagnosing high-risk brain diseases and predicting diseases such as Alzheimer's with symptoms challenging to predict and diseases with overlapping symptoms and overlapping symptoms and attribute values. The scope of the research work can be further extended to determine at which stage the epilepsy is present in a patient, in order to provide a correct diagnosis and medical treatment.