To solve the Protein folding problem is one of the most important task in computational biology. Protein secondary structure prediction is key step in prediction of protein tertiary structure. There have emerged many methods such as meta predictor based, neighbor based and model based methods to predict protein structure. The model based approaches employ machine learning techniques like neural networks and support vector machines to learn a predictive model trained on sequence of known structure. Historically machine learning methods have shown amazing results Therefore objective of this paper is to compare the performance of Neural Networks (NN) and Support Vector Machines (SVM) in predicting the secondary structure of proteins from their primary sequence. For each NN and SVM, we created classifiers to distinguish between helices (H) strand (E), and coil (C). Finally the output obtained illustrates that out of these top most novel methods for classification purpose Neural Networks performs much better then support vector machine and produces better efficiency in much lesser time.