Numerous biometric traits, including voice, handwriting, gait, iris, face, fingerprint, and palmprint have been proposed in recent years. A biometric authentication method that has gained popularity recently is palm print recognition. In the area of biometric identification, especially palm print identification, the methods of ML (Machine Learning) showed considerable potential. SVM (Support Vector Machine) become a widely used method in many applications such as palm print detection, with the emergence of machine learning techniques. This study suggests a Machine Learning based system for recognizing palm prints that include certain phases such as initial preprocessing, then feature extraction, and finally classification. This study offers a foundation for creating palm print identification systems that are both more precise and successful and it shows how well SVM works for palm print recognition. From the results obtained the proposed SVM gives accuracy of 91.60%, sensitivity of 0.92 and specificity 0.89 which is high compared to KNN accuracy of 88.92%, sensitivity of 0.89 and specificity 0.86 and RF accuracy of 89.90%, sensitivity of 0.91 and specificity 0.88.