The application of E-Learning types that correspond to the characteristics of the E-Learning system can be determined by the user by filling out a questionnaire about the characteristics of the E-Learning System. Many types of E-Learning that have been used by the institution. To determine the type of E-Learning that is appropriate to the characteristics of the E-Learning system can be done by the user by filling out the assessment questionnaire about the characteristics of the E-Learning System. The data processing results of the questionnaire to the application of the Neural Network with the Perceptron method. Neural network is an information processing system that has characteristics similar to a network of nerve biology. Perceptron is a simple network that is usually used to classify a particular type of pattern that is often known as a linear separation. From the calculations that researchers do manually or testing of the training data and test data in accordance with the training measures Perceptron defined in equation f (net) = t (yi), and error = 0 to determine kesusksesannya, then from training data and test data produces the correct target and in accordance with the expected results, which means that the method Perceptron applied were able to predict the type of E-Learning in accordance with the characteristics of E-Learning system is correct and produce the same target with the data results of the questionnaire from the user. Calculation of percentage of E-Learning used STMIK Hang Tuah Pekanbaru corresponding characteristics of the system of E-Learning and Evaluation Model ISO 9126 elearning.htp.ac.id results obtained with the value -1 = No, the performance of 20%, and a value of 1 = Yes, performance 80% and the error = 0 of 20 training data and test patterns. kuliah.htp.ac.id with a value of -1 = No, the performance of 45%, and a value of 1 = Yes, the performance of 55% and error = 0 of 20 training data and test patterns. edmodo.com/es3jelita with a value of -1 = No, the performance of 80%, and a value of 1 = Yes, the performance of 20% and error = 0 of 20 training data and test patterns.