Parkinson's disease (PD) is a long-term degenerative disorder of the central nervous system that mainly affects the motor system. Nowadays classification and prediction of Parkinson’s diseases is a burning issue.  We have used four machine learning techniques for Parkinson’s diseases classification and prediction. The data was extracted from UCI machine learning data repository.  This research showed that support vector machine with polynomial kernel achieve accuracy, sensitivity, specificity, positive predictive value, negative predictive value 0.86, 0.85, 0.88, 0.87 and 0.85 respectively and they are the maximum values.  his result makes the decision that support vector machine with polynomial kernel is the best classification and prediction method for Parkinson’s diseases.